threatdeck
Live 13:45 UTC ·

Security Skills Watch AI / LLM security Vendor: Semgrep ★ 351

llm-security

semgrep/skills/skills/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…”

From the skill's own SKILL.md front matter, by Semgrep; not reviewed or endorsed by ThreatDeck.

Scanner signals

No signals: none of our static rules matched the 5 file(s) we read. That is not a guarantee; read the skill before installing it.

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. Files read: 5, 9 not read (caps); scripts in folder: 0; binaries or archives: 0.

Source

Repository
semgrep/skills
Skill folder
skills/llm-security
SKILL.md
at commit 68177b8830f9
Publisher
Semgrep (vendor)
License
None stated: without a license, reuse rights are not granted.
Stars
351
Last push
2026-11-11
Found via
ThreatDeck source list
Scanned
2026-11-10
Also
Secure code review

Install from the original source

ThreatDeck links to the publisher's repository and does not host a copy. Read every file in the folder first; the commands below fetch exactly the commit we scanned.

Claude Code (personal skill)

git clone --filter=blob:none --no-checkout https://github.com/semgrep/skills.git /tmp/skill-semgrep-llm-security
git -C /tmp/skill-semgrep-llm-security sparse-checkout set --no-cone '/skills/llm-security/'
git -C /tmp/skill-semgrep-llm-security checkout 68177b8830f96cd9d10dacbb14dde2566360503d
# Read every file in the folder before copying it
mkdir -p ~/.claude/skills && cp -R /tmp/skill-semgrep-llm-security/'skills/llm-security' ~/.claude/skills/llm-security

For a project skill shared through the repository, copy the folder to .claude/skills/llm-security/ instead. For Codex, use ~/.agents/skills/llm-security/ (or .agents/skills/ in a repository) and restart Codex.

More from semgrep/skills

More in AI / LLM security

Following

Follow the vendors, products, AI tools, techniques and actors you care about. Matching stories, CVEs and exploited bugs are marked, a Following tab appears in the feed, and returning visits show what changed. Saved only in this browser.

Presets

Get updates

A personal RSS feed of new stories on everything you follow. Paste it into any feed reader, Slack or Teams RSS app.