Agent skills · AI security
Security Skills Watch
Public agent skills for security work (secure code review, threat modeling, secrets, detection and response, compliance, cloud, AI and MCP security), indexed from the official Anthropic and OpenAI repositories, security vendors and community collections. ThreatDeck does not write or re-host these skills: each entry quotes the skill's own description, links to its source at the commit we scanned and lists the red-flag patterns our static scanner found in its files.
How to install a skill safely · Method and rules · MCP Server Watch · scanned 2026-11-22
Signals, not a verdict: each one is a pattern our static scanner found in the skill's own files at the pinned commit. A clean result is not a guarantee; read a skill's files before you install it.
Skills
124 shown| Skill | Category | Source | License | Repo ★ | Signals |
|---|---|---|---|---|---|
| claude-security “Claude Security: scan the codebase (the whole repository or a scoped part of it), scan changes (this branch's or a pull request's diff, or one commit), or suggest patches (findings turned into targeted patch files, each verified by a panel of agents, that you apply when you choose). Use when the user asks to scan,…” anthropics/claude-plugins-official/plugins/claude-security/skills/claude-security | AppSec testing | Official Anthropic | Apache-2.0 | 47,920 | none |
| compliance-tracking “Track compliance requirements and audit readiness. Trigger with "compliance", "audit prep", "SOC 2", "ISO 27001", "GDPR", "regulatory requirement", or when the user needs help tracking, preparing for, or documenting compliance activities.” anthropics/knowledge-work-plugins/operations/skills/compliance-tracking | Compliance & GRC | Official Anthropic | Apache-2.0 | 36,658 | none |
| security-best-practices “Perform language and framework specific security best-practice reviews and suggest improvements. Trigger only when the user explicitly requests security best practices guidance, a security review/report, or secure-by-default coding help. Trigger only for supported languages (python, javascript/typescript, go). Do…” openai/skills/skills/.curated/security-best-practices | Secure code review | Official OpenAI | Apache-2.0 | 28,881 | none |
| security-ownership-map “Analyze git repositories to build a security ownership topology (people-to-file), compute bus factor and sensitive-code ownership, and export CSV/JSON for graph databases and visualization. Trigger only when the user explicitly wants a security-oriented ownership or bus-factor analysis grounded in git history (for…” openai/skills/skills/.curated/security-ownership-map | General security | Official OpenAI | Apache-2.0 | 28,881 | none |
| security-threat-model “Repository-grounded threat modeling that enumerates trust boundaries, assets, attacker capabilities, abuse paths, and mitigations, and writes a concise Markdown threat model. Trigger only when the user explicitly asks to threat model a codebase or path, enumerate threats/abuse paths, or perform AppSec threat…” openai/skills/skills/.curated/security-threat-model | AI / LLM security | Official OpenAI | Apache-2.0 | 28,881 | none |
| deep-security-scan “Use when the user asks for a deep, exhaustive, multi-pass, or variance-reducing repository-wide or scoped-path Codex Security scan. Run repeated complete independent Standard scans with the Codex Security deep-scan tool, which aggregates their validated findings and prepares the canonical artifacts; then complete…” openai/plugins/plugins/codex-security/skills/deep-security-scan | AppSec testing | Official OpenAI | none stated | 8,052 | none |
| define-security-policy “Define, review, or update SECURITY.md guidance for a repository or component. Use when the user wants to clarify what Codex Security should review, what is out of scope, which security properties must hold, or whether existing guidance still matches the code.” openai/plugins/plugins/codex-security/skills/define-security-policy | Compliance & GRC | Official OpenAI | none stated | 8,052 | none |
| finding-discovery “Use when Codex is already in the finding-discovery phase of a security scan or the user explicitly asks to discover candidate security findings in a repository or code change. Do not use as the primary trigger for full PR, commit, branch, patch, or repository scans.” openai/plugins/plugins/codex-security/skills/finding-discovery | AppSec testing | Official OpenAI | none stated | 8,052 | none |
| fix-finding “Use only when the user explicitly asks to fix and verify a validated or plausible security vulnerability. Do not use for ordinary bug fixes, correctness or design review findings, general validation, or full PR, commit, branch, patch, or repository scans.” openai/plugins/plugins/codex-security/skills/fix-finding | AppSec testing | Official OpenAI | none stated | 8,052 | none |
| propose-security-hardening “Develop evidence-backed structural and architectural security hardening proposals from vulnerability disclosures, supplied findings, incident or assessment documents, source code, or a completed Codex Security scan. Use when a user asks for systemic improvements, alternatives beyond per-finding patches,…” openai/plugins/plugins/codex-security/skills/propose-security-hardening | Secure code review | Official OpenAI | none stated | 8,052 | none |
| security-diff-scan “Review a pull request, commit, branch diff, or working-tree patch for security vulnerabilities.” openai/plugins/plugins/codex-security/skills/security-diff-scan | AppSec testing | Official OpenAI | none stated | 8,052 | none |
| security-scan “Use for a standard, single-pass security audit of an entire repository or a scoped path, package, folder, or submodule with no diff to review. This is the default repository scan. Do not use for PR, commit, branch, or working-tree diffs, or for deep, multi-pass scans.” openai/plugins/plugins/codex-security/skills/security-scan | AppSec testing | Official OpenAI | none stated | 8,052 | none |
| threat-model “Use when Codex is already in the threat-modeling phase of a security scan, the user explicitly invokes $threat-model, or the user explicitly asks to create, update, or persist a repository threat model. Do not use as the primary trigger for full PR, commit, branch, patch, or repository scans.” openai/plugins/plugins/codex-security/skills/threat-model | Threat modeling | Official OpenAI | none stated | 8,052 | none |
| track-findings “Track validated Codex Security findings in Linear, Jira, GitHub issues, or draft GitHub security advisories. Supports issue batches, duplicate checks, and reviewed writes. Do not use for scans or fixes.” openai/plugins/plugins/codex-security/skills/track-findings | AppSec testing | Official OpenAI | none stated | 8,052 | none |
| triage-finding “Triage supplied or imported security findings against a repository using its security policy and static code evidence. Accepts scanner reports, advisories, GitHub findings, and Jira or Linear tickets. Do not use for discovery, duplicate triage, runtime validation, or fixes.” openai/plugins/plugins/codex-security/skills/triage-finding | AppSec testing | Official OpenAI | none stated | 8,052 | none |
| twilio-compliance-traffic “Rules you must follow for Twilio messaging and voice traffic. Covers TCPA (consent tiers, quiet hours, DNC), GDPR (EU consent, right to deletion), PCI DSS (payment recording, Pay verb), HIPAA (BAA, PHI), FDCPA (debt collection limits), CAN-SPAM, WhatsApp policies, SHAKEN/STIR, and consent management patterns. Use…” openai/plugins/plugins/twilio-developer-kit/skills/twilio-compliance-traffic | Compliance & GRC | Official OpenAI | none stated | 8,052 | none |
| twilio-security-api-auth “Choose the right Twilio authentication method and implement it correctly. Covers Auth Token (testing only), API Keys (production standard), OAuth2 client_credentials (time-limited bearer tokens), Access Tokens (client-side SDKs), and test credentials. Use this skill before making any Twilio API calls in production.” openai/plugins/plugins/twilio-developer-kit/skills/twilio-security-api-auth | Secrets | Official OpenAI | none stated | 8,052 | none |
| twilio-security-compliance-hipaa “Configure Twilio accounts for HIPAA compliance. Covers BAA requirements, HIPAA Project designation (self-service and support), eligible services list, per-product requirements (Voice, SMS, ConversationRelay, Conversation Intelligence, Flex, Verify), message redaction, and what is NOT eligible. Use this skill when…” openai/plugins/plugins/twilio-developer-kit/skills/twilio-security-compliance-hipaa | Compliance & GRC | Official OpenAI | none stated | 8,052 | none |
| twilio-security-hardening “Secure Twilio applications against common attacks. Covers credential management (API keys vs auth tokens), request validation (webhook signature verification), PCI DSS compliance, HIPAA account requirements, SMS pumping prevention, geo-permissions, and account isolation patterns. Use this skill when developers are…” openai/plugins/plugins/twilio-developer-kit/skills/twilio-security-hardening | Secure code review | Official OpenAI | none stated | 8,052 | none |
| validation “Use when Codex is already in the validation phase of a security scan or the user explicitly asks to determine whether one or more candidate security findings are valid. Do not use as the primary trigger for full PR, commit, branch, patch, or repository scans.” openai/plugins/plugins/codex-security/skills/validation | AppSec testing | Official OpenAI | none stated | 8,052 | none |
| vercel-firewall “Vercel Firewall expert guidance — automatic DDoS mitigation, the Vercel WAF (custom rules, IP blocking, managed rulesets, rate limiting), Attack Mode, system bypass, bot management, and the `vercel firewall` CLI. Use when configuring platform-level security, responding to attacks, or staging firewall rules.” openai/plugins/plugins/vercel/skills/vercel-firewall | Cloud & IaC | Official OpenAI | none stated | 8,052 | none |
| verify-fix “Use only when the user explicitly requests verification that a security fix remediates a reported vulnerability. Do not invoke automatically while implementing fixes, reviewing ordinary code changes, or running tests. Do not use for non-security fixes, candidate finding validation, or full repository scans.” openai/plugins/plugins/codex-security/skills/verify-fix | AppSec testing | Official OpenAI | none stated | 8,052 | none |
| vulnerability-writeup “Turn vulnerability notes, disclosure reports, PoCs, source code, or Codex Security findings into self-contained, sceptically validated, natural-sounding vulnerability reports. Use for one vulnerability or a disclosure campaign; a Codex Security scan is optional.” openai/plugins/plugins/codex-security/skills/vulnerability-writeup | AppSec testing | Official OpenAI | none stated | 8,052 | none |
| api-gateway-backend-security-and-rate-limiting “Secures and rate limits backend services behind Google Cloud API Gateway across OpenAPI 2.0 and OpenAPI 3.0.x API configurations, including MCP-enabled gateways. Use when configuring API key or JWT authentication, locking down Cloud Run or Cloud Run functions backends with a gateway service account, reading…” google/skills/skills/cloud/api-gateway-backend-security-and-rate-limiting | Cloud & IaC | Vendor Google | Apache-2.0 | 24,527 | none |
| detection-engineering-coverage-evaluation “Automates the end-to-end detection engineering workflow in Google SecOps using MCP tools. Use when fetching threat intelligence from blogs, generating Threat Detection Opportunities (TDOs), simulating attacker behavior with synthetic UDM events, evaluating rule coverage, and deploying gap-closing rules. Don't use…” google/skills/skills/cloud/detection-engineering-coverage-evaluation | Detection & IR | Vendor Google | Apache-2.0 | 24,527 | none |
| gke-platform-security “Plans, configures, and hardens platform-level Google Kubernetes Engine (GKE) cluster security. Covers cluster add-ons (Secret Manager enablement), RBAC hardening (disabling insecure bindings, audit tools), Binary Authorization, Secrets Encryption (--database-encryption-key), Security Posture (--security-posture),…” google/skills/skills/cloud/gke-platform-security | Cloud & IaC | Vendor Google | Apache-2.0 | 24,527 | none |
| gke-workload-security “Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running security audits (`audit_cluster.sh`), enforcing Network Policies (default-deny and Dataplane V2 logging), isolating high-risk pods inside GKE Sandbox (`gVisor`), enforcing…” google/skills/skills/cloud/gke-workload-security | Cloud & IaC | Vendor Google | Apache-2.0 | 24,527 | none |
| google-cloud-solution-multi-agent-security “Designs, deploys, and secures Google Cloud Agent Gateway solutions. Use when the user needs to configure multi-agent security, ingress (CLIENT_TO_AGENT), or egress (AGENT_TO_ANYWHERE) patterns involving Model Armor, IAP, and Agent Registry. Don't use for general Cloud Load Balancing or basic VPC setup not related…” google/skills/skills/cloud/google-cloud-solution-multi-agent-security | Cloud & IaC | Vendor Google | Apache-2.0 | 24,527 | none |
| google-cloud-waf-security “Generates security-focused guidance for Google Cloud workloads based on the design principles and recommendations in the Google Cloud Well-Architected Framework (WAF). Use this skill to evaluate workloads, identify security requirements, and provide actionable recommendations for IAM, network security, data…” google/skills/skills/cloud/google-cloud-waf-security | Cloud & IaC | Vendor Google | Apache-2.0 | 24,527 | none |
| secops-detection-engineering “Author, validate, test, and deploy YARA-L 2.0 detection rules and evaluate end-to-end detection coverage gaps in Google SecOps. Use when writing new detection rules, tuning existing rules, validating syntax, testing logic against historical telemetry, or evaluating detection coverage against threat intelligence…” google/skills/skills/cloud/secops-detection-engineering | Detection & IR | Vendor Google | Apache-2.0 | 24,527 | none |
| secops-hunt “Expert guidance for proactive threat hunting in Google SecOps. Use when proactively hunting for threats, retroactively analyzing indicators of compromise (IoCs), performing prevalence searches across enterprise events, hunting for MITRE ATT&CK techniques, or detecting behavioral and statistical outliers using UDM…” google/skills/skills/cloud/secops-hunt | Detection & IR | Vendor Google | Apache-2.0 | 24,527 | 1 low |
| secops-triage “Expert guidance for security alert triage in Google SecOps. Use when investigating and triaging security alerts, determining false positives vs. true positives, assessing entity risk, adjusting alert severity or priority, and closing or escalating alerts and cases. Don't use for deep multi-hop incident…” google/skills/skills/cloud/secops-triage | Detection & IR | Vendor Google | Apache-2.0 | 24,527 | none |
| framework-compliance-triage “Make a cloud account compliant with a security or industry framework using Prowler Cloud.” prowler-cloud/prowler/claude_plugins/prowler/skills/framework-compliance-triage | Compliance & GRC | Vendor Prowler | Apache-2.0 | 15,301 | none |
| prowler “Main entry point for Prowler development - quick reference for all components. Trigger: General Prowler development questions, project overview, component navigation (NOT PR CI gates or GitHub Actions workflows).” prowler-cloud/prowler/skills/prowler | Cloud & IaC | Vendor Prowler | Apache-2.0 | 15,301 | 1 low |
| prowler-api “Prowler API patterns: RLS, RBAC, providers, Celery tasks, SSE. Trigger: When working in api/ on models/serializers/viewsets/filters/tasks involving tenant isolation (RLS), RBAC, provider lifecycle, Celery tasks or SSE endpoints.” prowler-cloud/prowler/skills/prowler-api | Cloud & IaC | Vendor Prowler | Apache-2.0 | 15,301 | 1 low |
| prowler-changelog Description withheld (markup or hidden text in the original). prowler-cloud/prowler/skills/prowler-changelog | Cloud & IaC | Vendor Prowler | Apache-2.0 | 15,301 | 1 low |
| prowler-ci “Helps with Prowler repository CI and PR gates (GitHub Actions workflows). Trigger: When investigating CI checks failing on a PR, PR title validation, changelog gate/no-changelog label, conflict marker checks, secret scanning, release freeze, CODEOWNERS/labeler automation, or anything under .github/workflows.” prowler-cloud/prowler/skills/prowler-ci | Cloud & IaC | Vendor Prowler | Apache-2.0 | 15,301 | 1 low |
| prowler-commit “Creates professional git commits for Prowler following conventional-commits format, with prek pre-commit hooks. Trigger: When creating commits, after completing code changes, when user asks to commit.” prowler-cloud/prowler/skills/prowler-commit | Cloud & IaC | Vendor Prowler | Apache-2.0 | 15,301 | none |
| prowler-compliance “Creates, syncs, audits and maintains Prowler compliance frameworks: universal multi-provider JSON (preferred) and legacy per-provider JSON, ConfigRequirements guardrails, output formatters, external compliance plug-ins (entry points), and check-to-requirement mapping audits. Trigger: When working with compliance…” prowler-cloud/prowler/skills/prowler-compliance | Compliance & GRC | Vendor Prowler | Apache-2.0 | 15,301 | 1 low |
| prowler-compliance-review “Reviews Pull Requests that add or modify Prowler compliance frameworks (universal multi-provider or legacy per-provider JSON, mappings, guardrails, formatters). Trigger: When reviewing PRs with compliance framework changes, CIS/NIST/PCI-DSS additions, or compliance JSON files.” prowler-cloud/prowler/skills/prowler-compliance-review | Compliance & GRC | Vendor Prowler | Apache-2.0 | 15,301 | 1 low |
| prowler-pr “Creates Pull Requests for Prowler following the project template and conventions. Trigger: When working on pull request requirements or creation (PR template sections, PR title Conventional Commits check, changelog gate/no-changelog label, backport labels), or when inspecting PR-related GitHub workflows like…” prowler-cloud/prowler/skills/prowler-pr | Cloud & IaC | Vendor Prowler | Apache-2.0 | 15,301 | 1 low |
| prowler-provider “Creates new Prowler providers (built-in or external plug-in) or adds services to existing providers. Trigger: When adding a new provider to the Prowler SDK, building an external provider plug-in (prowler.providers entry point), implementing the Provider contract (from_cli_args, get_scan_arguments,…” prowler-cloud/prowler/skills/prowler-provider | Cloud & IaC | Vendor Prowler | Apache-2.0 | 15,301 | 1 low |
| prowler-readme-table “Updates the "Prowler at a Glance" table in README.md with accurate provider statistics. Trigger: When updating README.md provider stats, checks count, services count, compliance frameworks, or categories.” prowler-cloud/prowler/skills/prowler-readme-table | Cloud & IaC | Vendor Prowler | Apache-2.0 | 15,301 | 1 low |
| prowler-registry-artifact “Packages Prowler checks, compliance frameworks (legacy and universal) and providers as external plug-in Python wheels discovered through entry points, and publishes them on the Prowler Registry. Trigger: When creating a pyproject.toml with prowler.checks.*, prowler.providers, prowler.compliance or…” prowler-cloud/prowler/skills/prowler-registry-artifact | Cloud & IaC | Vendor Prowler | Apache-2.0 | 15,301 | 1 low |
| prowler-sdk-check “Creates and updates Prowler SDK security checks (implementation, metadata, fixers, configurable checks). Trigger: When creating or updating a Prowler SDK security check or its metadata.json for any provider (AWS, Azure, GCP, Kubernetes, GitHub, M365, etc.), adding a check fixer, or making a check configurable via…” prowler-cloud/prowler/skills/prowler-sdk-check | Cloud & IaC | Vendor Prowler | Apache-2.0 | 15,301 | 1 low |
| prowler-test-api “Testing patterns for Prowler API: JSON:API, Celery tasks, RLS isolation, RBAC. Trigger: When writing tests for api/ (JSON:API requests/assertions, cross-tenant isolation, RBAC, Celery tasks, viewsets/serializers).” prowler-cloud/prowler/skills/prowler-test-api | Cloud & IaC | Vendor Prowler | Apache-2.0 | 15,301 | 1 low |
| prowler-test-mcp “Testing patterns for the Prowler MCP Server: in-memory FastMCP clients, the ProwlerAPIClient singleton, JSON:API model builders and mocked httpx transports. Trigger: When writing tests under mcp_server/tests/ (tools, models, api_client, auth, sub-servers).” prowler-cloud/prowler/skills/prowler-test-mcp | MCP & agent config | Vendor Prowler | Apache-2.0 | 15,301 | 1 low |
| prowler-test-sdk “Testing patterns for the Prowler SDK (Python): checks, services, fixers and providers. Trigger: When writing or fixing tests for the Prowler SDK (checks/services/fixers/providers under tests/), including AWS mocking with moto or botocore and MagicMock-based mocking for the other providers.” prowler-cloud/prowler/skills/prowler-test-sdk | Cloud & IaC | Vendor Prowler | Apache-2.0 | 15,301 | 1 low |
| prowler-test-ui “E2E testing patterns for Prowler UI (Playwright). Trigger: When writing Playwright E2E tests under ui/tests in the Prowler UI (Prowler-specific base page/helpers, tags, flows).” prowler-cloud/prowler/skills/prowler-test-ui | Cloud & IaC | Vendor Prowler | Apache-2.0 | 15,301 | 1 low |
| prowler-ui “Prowler UI-specific patterns. For generic patterns, see: typescript, react-19, nextjs-16, tailwind-4. Trigger: When working inside ui/ on Prowler-specific conventions (shadcn, folder placement, actions/adapters, shared types/hooks/lib).” prowler-cloud/prowler/skills/prowler-ui | Cloud & IaC | Vendor Prowler | Apache-2.0 | 15,301 | 1 low |
| address-sanitizer “Builds and runs code under AddressSanitizer to catch buffer overflows, use-after-free, and other memory errors during fuzzing or tests. Covers -fsanitize=address builds, ASAN_OPTIONS, reading the crash report, LeakSanitizer, and the overhead and platform trade-offs. Use when fuzzing C/C++ or Rust that has unsafe…” trailofbits/skills/plugins/testing-handbook-skills/skills/address-sanitizer | AppSec testing | Vendor Trail of Bits | CC-BY-SA-4.0 | 8,341 | none |
| aflpp “Sets up and runs AFL++ for multi-core fuzzing of C/C++ projects built with afl-clang-fast or afl-gcc-fast. Covers instrumentation modes, parallel main and secondary campaigns, persistent mode, corpus minimization, and crash triage. Use when scaling fuzzing across cores, fuzzing a mature C/C++ codebase, reading the…” trailofbits/skills/plugins/testing-handbook-skills/skills/aflpp | AppSec testing | Vendor Trail of Bits | CC-BY-SA-4.0 | 8,341 | none |
| agentic-actions-auditor “Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Detects attack vectors where attacker-controlled input reaches AI agents running in CI/CD pipelines, including env var intermediary patterns, direct…” trailofbits/skills/plugins/agentic-actions-auditor/skills/agentic-actions-auditor | MCP & agent config | Vendor Trail of Bits | CC-BY-SA-4.0 | 8,341 | 1 low |
| algorand-vulnerability-scanner “Scans Algorand smart contracts for 11 common vulnerabilities including rekeying attacks, unchecked transaction fees, missing field validations, and access control issues. Use when auditing Algorand projects (TEAL/PyTeal).” trailofbits/skills/plugins/building-secure-contracts/skills/algorand-vulnerability-scanner | AppSec testing | Vendor Trail of Bits | CC-BY-SA-4.0 | 8,341 | none |
| atheris “Sets up and runs Atheris, the coverage-guided Python fuzzer built on libFuzzer. Covers TestOneInput harnesses, FuzzedDataProvider, instrumenting both pure Python and native C extensions, and running under AddressSanitizer. Use when fuzzing a Python package, hunting memory corruption in a Python C extension, or…” trailofbits/skills/plugins/testing-handbook-skills/skills/atheris | AppSec testing | Vendor Trail of Bits | CC-BY-SA-4.0 | 8,341 | none |
| audit-context-building “Understand a codebase before looking for bugs in it - what each function assumes, what it guarantees, and what it depends on elsewhere. Use when starting an audit, threat model, or architecture review on unfamiliar code, and before any vulnerability-hunting pass.” trailofbits/skills/plugins/audit-context-building/skills/audit-context-building | Threat modeling | Vendor Trail of Bits | CC-BY-SA-4.0 | 8,341 | none |
| audit-prep-assistant “Prepares codebases for security review using Trail of Bits' checklist. Helps set review goals, runs static analysis tools, increases test coverage, removes dead code, ensures accessibility, and generates documentation (flowcharts, user stories, inline comments). Use when preparing your own codebase to be audited by…” trailofbits/skills/plugins/building-secure-contracts/skills/audit-prep-assistant | Secure code review | Vendor Trail of Bits | CC-BY-SA-4.0 | 8,341 | none |
| c-review “Performs comprehensive C/C++ security review for memory corruption, integer overflows, race conditions, and platform-specific vulnerabilities. Use when auditing native C/C++ applications, reviewing daemons or services for memory safety, or hunting integer overflow / use-after-free / race conditions in userspace code.” trailofbits/skills/plugins/c-review/skills/c-review | Secure code review | Vendor Trail of Bits | CC-BY-SA-4.0 | 8,341 | 1 low |
| cairo-vulnerability-scanner “Scans Cairo/StarkNet smart contracts for 6 critical vulnerabilities including felt252 arithmetic overflow, L1-L2 messaging issues, address conversion problems, and signature replay. Use when auditing StarkNet projects.” trailofbits/skills/plugins/building-secure-contracts/skills/cairo-vulnerability-scanner | AppSec testing | Vendor Trail of Bits | CC-BY-SA-4.0 | 8,341 | none |
| cargo-fuzz “Sets up and runs cargo-fuzz, the standard fuzzing tool for Cargo-based Rust projects. Covers cargo fuzz init, the nightly toolchain requirement, fuzz_target! harnesses, Arbitrary-derived structured inputs, sanitizer options, cargo fuzz coverage, and reproducing a crash artifact. Use when fuzzing a Rust crate,…” trailofbits/skills/plugins/testing-handbook-skills/skills/cargo-fuzz | AppSec testing | Vendor Trail of Bits | CC-BY-SA-4.0 | 8,341 | none |
| codeql “Scans a codebase for security vulnerabilities using CodeQL's interprocedural data flow and taint tracking analysis. Triggers on "run codeql", "codeql scan", "build codeql database", "SAST scan", "taint analysis", "dataflow analysis", or "find vulnerabilities in this repo". Covers Python, JavaScript/TypeScript, Go,…” trailofbits/skills/plugins/static-analysis/skills/codeql | AppSec testing | Vendor Trail of Bits | CC-BY-SA-4.0 | 8,341 | 1 low |
| constant-time-analysis “Detects timing side-channel vulnerabilities in cryptographic code. Use when implementing or reviewing crypto code, encountering division on secrets, secret-dependent branches, or constant-time programming questions in C, C++, Go, Rust, Swift, Java, Kotlin, C#, PHP, JavaScript, TypeScript, Python, or Ruby.” trailofbits/skills/plugins/constant-time-analysis/skills/constant-time-analysis | Secure code review | Vendor Trail of Bits | CC-BY-SA-4.0 | 8,341 | 1 low |
| constant-time-testing “Measures timing side channels in cryptographic implementations by running them, using dudect for statistical analysis and Timecop over Valgrind for dynamic tracing. Covers the formal, symbolic, dynamic, and statistical tool categories and how to read a result. Use when testing whether a running implementation is…” trailofbits/skills/plugins/testing-handbook-skills/skills/constant-time-testing | Secure code review | Vendor Trail of Bits | CC-BY-SA-4.0 | 8,341 | none |
| cosmos-vulnerability-scanner “Scans Cosmos SDK blockchain modules and CosmWasm contracts for consensus-critical vulnerabilities — chain halts, fund loss, state divergence. 25 core + 16 IBC + 10 EVM + 3 CosmWasm patterns. Use when auditing custom x/ modules, reviewing IBC integrations, or assessing pre-launch chain security. Updated for SDK v0.53.x.” trailofbits/skills/plugins/building-secure-contracts/skills/cosmos-vulnerability-scanner | AppSec testing | Vendor Trail of Bits | CC-BY-SA-4.0 | 8,341 | none |
| coverage-analysis “Measures and interprets what a fuzzing campaign actually reaches, using llvm-cov, lcov, or a fuzzer's own coverage output. Covers baselining a new campaign, reading coverage reports, and turning uncovered regions into harness, seed, or dictionary work. Use when a fuzzer plateaus, when judging whether a harness is…” trailofbits/skills/plugins/testing-handbook-skills/skills/coverage-analysis | AppSec testing | Vendor Trail of Bits | CC-BY-SA-4.0 | 8,341 | none |
| cvss-scoring “Produces CVSS v4.0 vector strings from plain-text vulnerability descriptions by systematically evaluating base metrics. Use when scoring a vulnerability, generating a CVSS vector, or estimating severity.” trailofbits/skills/plugins/cvss-scoring/skills/cvss-scoring | AppSec testing | Vendor Trail of Bits | CC-BY-SA-4.0 | 8,341 | none |
| differential-review “Performs security-focused differential review of code changes. Adapts analysis depth to codebase size, uses git blame for context, calculates blast radius by counting callers, checks test coverage of modified code, and generates a markdown report. Use when reviewing a PR, commit, or diff for security…” trailofbits/skills/plugins/differential-review/skills/differential-review | Secure code review | Vendor Trail of Bits | CC-BY-SA-4.0 | 8,341 | 1 low |
| firebase-apk-scanner “Scans Android APKs for Firebase security misconfigurations including open databases, storage buckets, authentication issues, and exposed cloud functions. Use when analyzing APK files for Firebase vulnerabilities, performing mobile app security audits, or testing Firebase endpoint security. For authorized security…” trailofbits/skills/plugins/firebase-apk-scanner/skills/firebase-apk-scanner | AppSec testing | Vendor Trail of Bits | CC-BY-SA-4.0 | 8,341 | none |
| fp-check “Systematically verifies suspected security bugs to eliminate false positives, producing a TRUE POSITIVE or FALSE POSITIVE verdict with documented evidence for each. Use when asked whether a specific finding is real, exploitable, or a false positive, or to verify or validate a suspected vulnerability — not for…” trailofbits/skills/plugins/fp-check/skills/fp-check | AppSec testing | Vendor Trail of Bits | CC-BY-SA-4.0 | 8,341 | 1 low |
| graph-evolution “Compares Trailmark code graphs at two source code snapshots (git commits, tags, or directories) to surface security-relevant structural changes. Detects new attack paths, complexity shifts, blast radius growth, taint propagation changes, and privilege boundary modifications that text diffs miss. Use when comparing…” trailofbits/skills/plugins/trailmark/skills/graph-evolution | Secure code review | Vendor Trail of Bits | CC-BY-SA-4.0 | 8,341 | none |
| mermaid-to-proverif “Translates Mermaid sequenceDiagrams describing cryptographic protocols into ProVerif formal verification models (.pv files). Use when generating a ProVerif model, formally verifying a protocol, converting a Mermaid diagram to ProVerif, verifying protocol security properties (secrecy, authentication, forward…” trailofbits/skills/plugins/trailmark/skills/mermaid-to-proverif | Secure code review | Vendor Trail of Bits | CC-BY-SA-4.0 | 8,341 | none |
| post-patch-validation “Validates security patches with reproducible baseline-versus-patched evidence, including original exploits, root-cause variants, behavior preservation, regressions, and newly introduced security failures. Use after a patch exists and before accepting, merging, or reporting it as fixed; also use when an AI-generated…” trailofbits/skills/plugins/post-patch-validation/skills/post-patch-validation | Secure code review | Vendor Trail of Bits | CC-BY-SA-4.0 | 8,341 | 1 low |
| rust-review “Performs comprehensive Rust security review for safe/unsafe boundary issues, memory safety in unsafe blocks, concurrency hazards, panic-induced DoS, FFI safety, and async runtime mistakes. Use when auditing Rust crates, services, or libraries — particularly those with `unsafe`, FFI, or concurrent code.” trailofbits/skills/plugins/rust-review/skills/rust-review | Secure code review | Vendor Trail of Bits | CC-BY-SA-4.0 | 8,341 | 1 low |
| sarif-parsing “Parses and processes SARIF files from static analysis tools like CodeQL, Semgrep, or other scanners. Triggers on "parse sarif", "read scan results", "aggregate findings", "deduplicate alerts", or "process sarif output". Handles filtering, deduplication, format conversion, and CI/CD integration of SARIF data. Does…” trailofbits/skills/plugins/static-analysis/skills/sarif-parsing | AppSec testing | Vendor Trail of Bits | CC-BY-SA-4.0 | 8,341 | 1 low |
| secure-workflow-guide “Guides through Trail of Bits' 5-step secure development workflow. Runs Slither scans, checks special features (upgradeability/ERC conformance/token integration), generates visual security diagrams, helps document security properties for fuzzing/verification, and reviews manual security areas. Use when securing a…” trailofbits/skills/plugins/building-secure-contracts/skills/secure-workflow-guide | AppSec testing | Vendor Trail of Bits | CC-BY-SA-4.0 | 8,341 | none |
| semgrep “Runs a Semgrep security scan over a codebase: detects languages, selects rulesets, presents the plan for explicit approval, then runs every approved ruleset through scripts/run-scans.sh, which batches the semgrep processes and writes scans.json, and merges the output to SARIF. Supports two scan modes, "run all" for…” trailofbits/skills/plugins/static-analysis/skills/semgrep | AppSec testing | Vendor Trail of Bits | CC-BY-SA-4.0 | 8,341 | 1 low |
| semgrep-rule-creator “Creates custom Semgrep rules for detecting security vulnerabilities, bug patterns, and code patterns. Use when writing Semgrep rules or building custom static analysis detections.” trailofbits/skills/plugins/semgrep-rule-creator/skills/semgrep-rule-creator | AppSec testing | Vendor Trail of Bits | CC-BY-SA-4.0 | 8,341 | 1 low |
| semgrep-rule-variant-creator “Creates language variants of existing Semgrep rules. Use when porting a Semgrep rule to specified target languages. Takes an existing rule and target languages as input, produces independent rule+test directories for each language.” trailofbits/skills/plugins/semgrep-rule-variant-creator/skills/semgrep-rule-variant-creator | AppSec testing | Vendor Trail of Bits | CC-BY-SA-4.0 | 8,341 | 1 low |
| sharp-edges “Identifies error-prone APIs, dangerous configurations, and footgun designs that enable security mistakes. Use when reviewing API designs, configuration schemas, cryptographic library ergonomics, or evaluating whether code follows 'secure by default' and 'pit of success' principles. Triggers: footgun,…” trailofbits/skills/plugins/sharp-edges/skills/sharp-edges | Secure code review | Vendor Trail of Bits | CC-BY-SA-4.0 | 8,341 | 2 low |
| solana-vulnerability-scanner “Scans Solana programs for 6 critical vulnerabilities including arbitrary CPI, improper PDA validation, missing signer/ownership checks, and sysvar spoofing. Use when auditing Solana/Anchor programs.” trailofbits/skills/plugins/building-secure-contracts/skills/solana-vulnerability-scanner | AppSec testing | Vendor Trail of Bits | CC-BY-SA-4.0 | 8,341 | none |
| substrate-vulnerability-scanner “Scans Substrate/Polkadot pallets for 7 critical vulnerabilities including arithmetic overflow, panic DoS, incorrect weights, and bad origin checks. Use when auditing Substrate runtimes or FRAME pallets.” trailofbits/skills/plugins/building-secure-contracts/skills/substrate-vulnerability-scanner | AppSec testing | Vendor Trail of Bits | CC-BY-SA-4.0 | 8,341 | none |
| supply-chain-risk-auditor “Audits a project's dependencies for supply-chain risk: version-matched advisories for direct dependencies and the full lockfile tree, abandoned or archived upstreams, npm publisher concentration, and install-time script execution. Use when asked to audit dependencies, assess supply-chain or third-party package…” trailofbits/skills/plugins/supply-chain-risk-auditor/skills/supply-chain-risk-auditor | Supply chain | Vendor Trail of Bits | CC-BY-SA-4.0 | 8,341 | 1 low |
| ton-vulnerability-scanner “Scans TON (The Open Network) smart contracts for 3 critical vulnerabilities including integer-as-boolean misuse, fake Jetton contracts, and forward TON without gas checks. Use when auditing FunC contracts.” trailofbits/skills/plugins/building-secure-contracts/skills/ton-vulnerability-scanner | AppSec testing | Vendor Trail of Bits | CC-BY-SA-4.0 | 8,341 | none |
| wycheproof “Validates cryptographic implementations against Project Wycheproof's test vectors, which encode known attacks and edge cases across AES, RSA, ECDSA, ECDH, and more. Covers loading test vectors, mapping result flags onto pass and fail expectations, and reading a failure. Use when testing a crypto implementation…” trailofbits/skills/plugins/testing-handbook-skills/skills/wycheproof | Secure code review | Vendor Trail of Bits | CC-BY-SA-4.0 | 8,341 | none |
| yara-rule-authoring “Guides authoring of high-quality YARA-X detection rules for malware identification. Use when writing, reviewing, or optimizing YARA rules. Covers naming conventions, string selection, performance optimization, migration from legacy YARA, and false positive reduction. Triggers on: YARA, YARA-X, malware detection,…” trailofbits/skills/plugins/yara-authoring/skills/yara-rule-authoring | Detection & IR | Vendor Trail of Bits | CC-BY-SA-4.0 | 8,341 | 1 low |
| azure-compliance “Run Azure compliance and security audits with azqr plus Key Vault expiration checks. Covers best-practice assessment, resource review, policy/compliance validation, and security posture checks. WHEN: compliance scan, security audit, BEFORE running azqr (compliance cli tool), Azure best practices, Key Vault…” microsoft/skills/.github/plugins/azure-skills/skills/azure-compliance | Compliance & GRC | Vendor Microsoft | MIT | 3,232 | none |
| azure-keyvault-certificates-rust “Azure Key Vault Certificates library for Rust. Create, manage, and use X.509 certificates including self-signed and CA-issued. Triggers: "keyvault certificates rust", "CertificateClient rust", "create certificate rust", "self-signed certificate rust", "X.509 rust".” microsoft/skills/.github/plugins/azure-sdk-rust/skills/azure-keyvault-certificates-rust | Secrets | Vendor Microsoft | MIT | 3,232 | none |
| azure-keyvault-keys-rust “Azure Key Vault Keys library for Rust. Create, manage, and use cryptographic keys including RSA, EC, and HSM-protected keys. Triggers: "keyvault keys rust", "KeyClient rust", "create key rust", "encrypt rust", "wrap key rust", "sign rust".” microsoft/skills/.github/plugins/azure-sdk-rust/skills/azure-keyvault-keys-rust | Secrets | Vendor Microsoft | MIT | 3,232 | none |
| azure-keyvault-keys-ts “Manage cryptographic keys using Azure Key Vault Keys SDK for JavaScript (@azure/keyvault-keys). Use when creating, encrypting/decrypting, signing, or rotating keys.” microsoft/skills/.github/plugins/azure-sdk-typescript/skills/azure-keyvault-keys-ts | Secrets | Vendor Microsoft | MIT | 3,232 | none |
| azure-keyvault-py “Azure Key Vault SDK for Python. Use for secrets, keys, and certificates management with secure storage. Triggers: "key vault", "SecretClient", "KeyClient", "CertificateClient", "secrets", "encryption keys".” microsoft/skills/.github/plugins/azure-sdk-python/skills/azure-keyvault-py | Secrets | Vendor Microsoft | MIT | 3,232 | none |
| azure-keyvault-secrets-rust “Azure Key Vault Secrets library for Rust. Store and retrieve secrets, passwords, and API keys. Triggers: "keyvault secrets rust", "SecretClient rust", "get secret rust", "set secret rust", "list secrets rust".” microsoft/skills/.github/plugins/azure-sdk-rust/skills/azure-keyvault-secrets-rust | Secrets | Vendor Microsoft | MIT | 3,232 | none |
| azure-keyvault-secrets-ts “Manage secrets using Azure Key Vault Secrets SDK for JavaScript (@azure/keyvault-secrets). Use when storing and retrieving application secrets or configuration values.” microsoft/skills/.github/plugins/azure-sdk-typescript/skills/azure-keyvault-secrets-ts | Secrets | Vendor Microsoft | MIT | 3,232 | none |
| azure-security-keyvault-keys-dotnet “Azure Key Vault Keys SDK for .NET. Client library for managing cryptographic keys in Azure Key Vault and Managed HSM. Use for key creation, rotation, encryption, decryption, signing, and verification. Triggers: "Key Vault keys", "KeyClient", "CryptographyClient", "RSA key", "EC key", "encrypt decrypt .NET", "key…” microsoft/skills/.github/plugins/azure-sdk-dotnet/skills/azure-security-keyvault-keys-dotnet | Secrets | Vendor Microsoft | MIT | 3,232 | none |
| azure-security-keyvault-keys-java “Azure Key Vault Keys Java SDK for cryptographic key management. Use when creating, managing, or using RSA/EC keys, performing encrypt/decrypt/sign/verify operations, or working with HSM-backed keys.” microsoft/skills/.github/plugins/azure-sdk-java/skills/azure-security-keyvault-keys-java | Secrets | Vendor Microsoft | MIT | 3,232 | none |
| azure-security-keyvault-secrets-java “Azure Key Vault Secrets Java SDK for secret management. Use when storing, retrieving, or managing passwords, API keys, connection strings, or other sensitive configuration data.” microsoft/skills/.github/plugins/azure-sdk-java/skills/azure-security-keyvault-secrets-java | Secrets | Vendor Microsoft | MIT | 3,232 | none |
| gha-security-review “GitHub Actions security review for workflow exploitation vulnerabilities. Use when asked to "review GitHub Actions", "audit workflows", "check CI security", "GHA security", "workflow security review", or review .github/workflows/ for pwn requests, expression injection, credential theft, and supply chain attacks.…” getsentry/skills/skills/gha-security-review | Secure code review | Vendor Sentry | Apache-2.0 | 1,193 | 3 low |
| security-model “Define, review, or update SECURITY_MODEL.md files that tell security review tools a repository's threat model, trust boundaries, invariants, reportable finding classes, and exclusions. Use when asked to "write a security model", "threat model this repo for scanners", "define security review scope", "what counts as…” getsentry/skills/skills/security-model | AI / LLM security | Vendor Sentry | Apache-2.0 | 1,193 | 1 low |
| security-review “Security code review for vulnerabilities. Use when asked to "security review", "find vulnerabilities", "check for security issues", "audit security", "OWASP review", or review code for injection, XSS, authentication, authorization, cryptography issues. Provides systematic review with confidence-based reporting.” getsentry/skills/skills/security-review | Secure code review | Vendor Sentry | LICENSE | 1,193 | 2 low |
| security-alert-analysis “Investigate a specific Elastic Security detection alert: gather context, assess entity risk, classify the threat, document findings, and optionally acknowledge. Use when triaging a single known alert, performing SOC investigation, or following up after the security-alert-triage skill identifies a group to investigate.” elastic/agent-skills/skills/security/alert-analysis | Detection & IR | Vendor Elastic | Apache-2.0 | 612 | none |
| security-alert-triage “Prioritize and rank the Elastic Security alert queue by weighted risk — base risk score, MITRE tactic boost, entity risk, and asset criticality — then cluster alerts into entity groups. Use when an analyst asks what to focus on, which alerts are most urgent, or wants a ranked starting point across the queue before…” elastic/agent-skills/skills/security/alert-triage | Detection & IR | Vendor Elastic | Apache-2.0 | 612 | none |
| security-case-management “Create, search, update, and manage SOC cases via the Kibana Cases API. Use when tracking incidents, linking alerts to cases, adding investigation notes, or managing triage output.” elastic/agent-skills/skills/security/case-management | Detection & IR | Vendor Elastic | Apache-2.0 | 612 | none |
| security-detection-rule-management “Create, tune, and manage Elastic Security detection rules (SIEM and Endpoint). Use for false positives, exceptions, new coverage, noisy rules, or rule management via Kibana API.” elastic/agent-skills/skills/security/detection-rule-management | Detection & IR | Vendor Elastic | Apache-2.0 | 612 | none |
| security-generate-security-sample-data “Generate sample security events, attack scenarios, and synthetic alerts for Elastic Security. Use when demoing, populating dashboards, testing detection rules, or setting up a POC.” elastic/agent-skills/skills/security/generate-security-sample-data | Detection & IR | Vendor Elastic | Apache-2.0 | 612 | 1 high |
| security-ml-integrations “Install and manage Elastic security ML integration packages (beaconing, ded, dga, lmd, pad, problemchild). Handles the full lifecycle: pre-flight checks, Fleet package install, component templates, ingest pipelines, transforms, data views, ML anomaly detection jobs, and detection rules. Use when a user asks to…” elastic/agent-skills/skills/security/ml-integrations | Detection & IR | Vendor Elastic | Apache-2.0 | 612 | none |
| slowmist-agent-security “Comprehensive security review framework for AI agents. Covers skill/MCP installation, GitHub repos, URLs/documents, on-chain addresses, products/services, and social shares. Built from real-world attack patterns and incident response experience.” slowmist/slowmist-agent-security | MCP & agent config | Vendor SlowMist | MIT | 561 | 2 low |
| openai-security-best-practices “Perform language and framework specific security best-practice reviews and suggest improvements. Trigger only when the user explicitly requests security best practices guidance, a security review/report, or secure-by-default coding help. Trigger only for supported languages (python, javascript/typescript, go). Do…” trailofbits/skills-curated/plugins/openai-security-best-practices/skills/openai-security-best-practices | Secure code review | Vendor Trail of Bits | CC-BY-SA-4.0 | 540 | none |
| openai-security-ownership-map “Analyze git repositories to build a security ownership topology (people-to-file), compute bus factor and sensitive-code ownership, and export CSV/JSON for graph databases and visualization. Trigger only when the user explicitly wants a security-oriented ownership or bus-factor analysis grounded in git history (for…” trailofbits/skills-curated/plugins/openai-security-ownership-map/skills/openai-security-ownership-map | General security | Vendor Trail of Bits | CC-BY-SA-4.0 | 540 | none |
| openai-security-threat-model “Repository-grounded threat modeling that enumerates trust boundaries, assets, attacker capabilities, abuse paths, and mitigations, and writes a concise Markdown threat model. Trigger only when the user explicitly asks to threat model a codebase or path, enumerate threats/abuse paths, or perform AppSec threat…” trailofbits/skills-curated/plugins/openai-security-threat-model/skills/openai-security-threat-model | Threat modeling | Vendor Trail of Bits | CC-BY-SA-4.0 | 540 | none |
| security-awareness “Teaches agents to recognize and avoid security threats during normal activity. Covers phishing detection, credential protection, domain verification, and social engineering defense. Use when building or operating agents that access email, credential vaults, web browsers, or sensitive data.” trailofbits/skills-curated/plugins/security-awareness/skills/security-awareness | General security | Vendor Trail of Bits | CC-BY-SA-4.0 | 540 | none |
| ghost-report “Ghost Security — combined security report. Aggregates findings from all scan skills (scan-deps, scan-secrets, scan-code) into a single prioritized report focused on the highest risk, highest confidence issues. Use when the user requests a security overview, vulnerability summary, full security audit, or combined…” ghostsecurity/skills/plugins/ghost/skills/report | AppSec testing | Vendor Ghost Security | apache-2.0 | 446 | 1 low |
| ghost-scan-code “Ghost Security - SAST code scanner. Finds security vulnerabilities in source code by planning and executing targeted scans for issues like SQL injection, XSS, BOLA, BFLA, SSRF, and other OWASP categories. Supports applications (backend, frontend, mobile) and libraries (prototype pollution, unsafe deserialization,…” ghostsecurity/skills/plugins/ghost/skills/scan-code | AppSec testing | Vendor Ghost Security | apache-2.0 | 446 | 1 low |
| ghost-scan-deps “Ghost Security - Software Composition Analysis (SCA) scanner. Scans dependency lockfiles for known vulnerabilities, identifies CVEs, and generates findings with severity levels and remediation guidance. Use when the user asks about dependency vulnerabilities, vulnerable packages, CVE checks, security audits of…” ghostsecurity/skills/plugins/ghost/skills/scan-deps | AppSec testing | Vendor Ghost Security | apache-2.0 | 446 | 1 low |
| ghost-scan-secrets “Ghost Security - Secrets and credentials scanner. Scans codebase for leaked API keys, tokens, passwords, and sensitive data. Detects hardcoded secrets and generates findings with severity and remediation guidance. Use when the user asks to check for leaked secrets, scan for credentials, find hardcoded API keys or…” ghostsecurity/skills/plugins/ghost/skills/scan-secrets | Secrets | Vendor Ghost Security | apache-2.0 | 446 | 1 low |
| ghost-validate “This skill should be used when the user asks to "validate a finding", "check if a vulnerability is real", "triage a security finding", "confirm a vulnerability", "determine if a finding is a true positive or false positive", or provides a security finding for review. It validates security vulnerability findings by…” ghostsecurity/skills/plugins/ghost/skills/validate | AppSec testing | Vendor Ghost Security | apache-2.0 | 446 | none |
| code-security “Security guidelines for writing secure code. Use when writing code, reviewing code for vulnerabilities, or asking about secure coding practices like 'check for SQL injection' or 'review security'. IMPORTANT: Always consult this skill when writing or reviewing any code that handles user input, authentication, file…” semgrep/skills/skills/code-security | Secure code review | Vendor Semgrep | none stated | 351 | none |
| llm-security “Security guidelines for LLM applications based on OWASP Top 10 for LLM 2025. Use when building LLM apps, reviewing AI security, implementing RAG systems, or asking about LLM vulnerabilities like 'prompt injection' or 'check LLM security'. IMPORTANT: Always consult this skill when building chatbots, AI agents, RAG…” semgrep/skills/skills/llm-security | AI / LLM security | Vendor Semgrep | none stated | 351 | none |
| semgrep “Run Semgrep static analysis scans and create custom detection rules. Use when asked to scan code with Semgrep, find security vulnerabilities, write custom YAML rules, or detect specific bug patterns. IMPORTANT: Also use this skill when users ask to 'scan for bugs', 'check code quality', 'find vulnerabilities',…” semgrep/skills/skills/semgrep | AppSec testing | Vendor Semgrep | none stated | 351 | none |
| Threat Designer “Run a threat-model-driven security review of the current repository using the threat-designer CLI. Analyzes the codebase, generates an architecture diagram, runs STRIDE-based threat modeling, and produces an actionable tasks.md with security findings.” awslabs/threat-designer/cli/kiro/skill | Threat modeling | Vendor AWS Labs | Apache-2.0 | 296 | none |
| dd-audit-compliance-report “Generate auditor-ready compliance evidence from Datadog Audit Trail for SOC 2 and PCI DSS. Maps framework controls to specific query patterns and produces formatted output.” datadog-labs/agent-skills/dd-audit/compliance-report | Compliance & GRC | Vendor Datadog | MIT | 185 | none |
| dd-audit-key-compromise “Investigate a potentially compromised Datadog API key — timeline of actions, geo/IP breakdown, endpoints called, anomaly flags, and remediation steps.” datadog-labs/agent-skills/dd-audit/key-compromise | Detection & IR | Vendor Datadog | MIT | 185 | none |
| dd-audit-security-investigation “Answer "who did what" security questions from Audit Trail — deletions, config changes, login activity, permission changes, actions from a specific user or IP.” datadog-labs/agent-skills/dd-audit/security-investigation | Compliance & GRC | Vendor Datadog | MIT | 185 | none |
| seal-frameworks “Use for questions about SEAL Security Frameworks — the Security Alliance's Web3/crypto security guidance. Covers wallet security, seed phrase management, multisig operations, transaction verification, incident response, SEAL 911, war room procedures, postmortems, runbooks, ENS, infrastructure, DNS security, supply…” security-alliance/frameworks | AI / LLM security | Vendor Security Alliance (SEAL) | Custom (see LICENSE) | 99 | none |
| genai-security-advisor “Grounds answers about GenAI/LLM/agentic AI security in the OWASP GenAI Security Project's published research -- the LLM Top 10, the Agentic Top 10, Data Security risk/framework mappings, MCP server security, AI red-teaming, incident response, and governance/maturity guidance. Use when reviewing code, architecture,…” GenAI-Security-Project/GenAI-Security-Advisor | AI / LLM security | Vendor OWASP GenAI Security Project | Apache-2.0 | 14 | none |
| genai-security-advisor GenAI-Security-Project/GenAI-Security-Advisor/skills/genai-security-advisor | AI / LLM security | Vendor OWASP GenAI Security Project | Apache-2.0 | 14 | none |
How to install a skill safely
- Read it first. A skill is instructions plus optional scripts that your agent follows with your permissions. Open the source folder at the pinned commit (every detail page links it) and read SKILL.md and every bundled script. Anthropic's guidance is to use skills only from trusted sources and to audit any other skill thoroughly before use.
- Claude Code: put the skill folder (with its SKILL.md) in
~/.claude/skills/<name>/for yourself, or.claude/skills/<name>/in a repository to share it with the project. Skills that ship inside a plugin marketplace install with/plugin marketplace add owner/repoand/plugin install <plugin>@<marketplace>; review the plugin details before choosing a scope. - Codex: user skills live in
~/.agents/skills/and repository skills in.agents/skills/; restart Codex after adding one. - Pin what you reviewed. Copy the folder at the commit you read rather than tracking a branch, and re-review on update: a skill can change after you approved it.
- Watch the grants.
allowed-toolsin a skill's front matter pre-approves tools while the skill is active; an unscopedBashgrant lets any command run without a prompt.
Sources: Claude Code docs: skills · Claude Code docs: install plugins · Agent Skills overview (security considerations) · Codex docs: skills · Agent Skills specification
Coverage by source
18 repositories| Repository | Publisher | Found via | Stars | Listed | Held |
|---|---|---|---|---|---|
| trailofbits/skills | Vendor Trail of Bits | ThreatDeck source list | 8,341 | 35 | 0 |
| prowler-cloud/prowler | Vendor Prowler | ThreatDeck source list | 15,301 | 18 | 1 |
| openai/plugins | Official OpenAI | ThreatDeck source list | 8,052 | 18 | 1 |
| microsoft/skills | Vendor Microsoft | ThreatDeck source list | 3,232 | 10 | 0 |
| google/skills | Vendor Google | ThreatDeck source list | 24,527 | 9 | 0 |
| elastic/agent-skills | Vendor Elastic | ThreatDeck source list | 612 | 6 | 0 |
| ghostsecurity/skills | Vendor Ghost Security | ThreatDeck source list | 446 | 5 | 0 |
| trailofbits/skills-curated | Vendor Trail of Bits | ThreatDeck source list | 540 | 4 | 1 |
| openai/skills | Official OpenAI | ThreatDeck source list | 28,881 | 3 | 0 |
| getsentry/skills | Vendor Sentry | ThreatDeck source list | 1,193 | 3 | 0 |
| semgrep/skills | Vendor Semgrep | ThreatDeck source list | 351 | 3 | 0 |
| datadog-labs/agent-skills | Vendor Datadog | ThreatDeck source list | 185 | 3 | 0 |
| GenAI-Security-Project/GenAI-Security-Advisor | Vendor OWASP GenAI Security Project | ThreatDeck source list | 14 | 2 | 0 |
| anthropics/claude-plugins-official | Official Anthropic | ThreatDeck source list | 47,920 | 1 | 0 |
| anthropics/knowledge-work-plugins | Official Anthropic | ThreatDeck source list | 36,658 | 1 | 0 |
| slowmist/slowmist-agent-security | Vendor SlowMist | ThreatDeck source list | 561 | 1 | 0 |
| awslabs/threat-designer | Vendor AWS Labs | ThreatDeck source list | 296 | 1 | 0 |
| security-alliance/frameworks | Vendor Security Alliance (SEAL) | ThreatDeck source list | 99 | 1 | 0 |
Method and rules
- Discovery: a reviewed list of official, vendor and community repositories, GitHub repository and SKILL.md code search, and security entries of curated awesome lists. Every repository is checked through the GitHub API; discovered ones need ≥25 stars and must not be forks.
- A skill is listed when its own name, description or folder carries a security term (one passing mention is not enough). At most 300 skills, taken round-robin across repositories so no single collection dominates; large collections are capped per repository.
- Name and description are quoted from the skill's front matter (whitespace collapsed, long text truncated); a description with markup or hidden characters is withheld. Categories are assigned by keyword rules from the skill's own text and can be wrong.
- Dual-use policy: skills whose name or description is about exploitation, penetration testing, red teaming, evasion or CTFs are counted but not listed until an editor reviews them (3 held). Listing is not endorsement.
- License comes from the skill's front matter, a LICENSE file in its folder, or the repository (GitHub). Stars and last push are repository facts.
- The scanner reads SKILL.md plus up to 8 scripts, 4 reference documents and 3 config files per skill (≤200 KB each) at the pinned commit. Patterns that a skill only discusses (review, negation or detection context) are not counted in prose; findings in reference documents are capped at low. Plugin-level hooks and MCP servers outside the skill folder are not scanned.
| Signal | What it means |
|---|---|
| Pipes a download into a shell | Downloads a script and runs it in one step (for example curl … | sh), so the code that runs is never reviewed and can change at any time. |
| Decodes and executes | Decodes an encoded string (base64 or similar) and executes the result, which hides what actually runs. |
| Downloads then runs a file | Saves a remote file and then makes it executable or runs it. |
| Runs packages fetched at run time | Runs a package straight from a registry or git URL (npx -y, uvx, pip install git+…), so the version that runs is whatever is published at the time. |
| Long encoded blob | Contains a long base64 or hex string that cannot be reviewed by reading it. |
| Hidden Unicode | Contains invisible or direction-changing characters (zero-width, bidirectional controls or Unicode tag characters) that can hide text from a human reviewer while the model still reads it. |
| Instructions in hidden comments | An HTML comment that does not render on GitHub contains instructions the model will still read. |
| Request-capture or tunnel endpoint | References a service commonly used to receive captured data or expose local ports (webhook catchers, tunnels, chat webhooks, paste sites). |
| Reads credential files | Reads or sends files that hold credentials (SSH keys, cloud credentials, token stores, agent login files). |
| Dumps environment variables | Collects all environment variables, which usually include API keys and tokens. |
| Turns off agent safety controls | Uses or tells the agent to use flags or settings that skip permission prompts, approvals or the sandbox. |
| Writes agent or shell config | Writes to shell profiles, scheduled tasks, git hooks, CI workflows or agent settings and instruction files, which persists beyond the task. |
| Destructive command | Contains a command that deletes a home or root directory or overwrites a disk. |
| Injection-style phrasing | Uses wording typical of prompt injection: overriding earlier instructions or acting without telling the user. |
| Bundled binary or archive | Ships compiled files or archives that cannot be reviewed by reading them. |
| Unscoped shell grant | The front matter pre-approves the shell tool without a command pattern (allowed-tools: Bash), so any command runs without a prompt while the skill is active. |