threatdeck
Live 13:45 UTC ·

AI security, today

3 AI-security stories in 24 hours · last 7 days: 2 exploited · 46 to patch · 10 to hunt

Updated 13:45 UTC · just now Next refresh 14:00 UTC 1 new in the last hour

Know the day a vulnerability hits the AI coding tools and MCP servers your developers run.

Free, no account · 70,291 MCP servers checked · 40 detections · every story source-linked

94
 
42
 
35
 
36
 

Top right now

Last 72h · ranked by importance

I need to…

All playbooks
  1. Red-team an LLM application9 steps
  2. Secure AI coding tools in your organisation8 steps
  3. Lock down MCP servers and clients8 steps
  4. Secure RAG and vector stores8 steps
  5. Give AI agents identity and least privilege8 steps
  6. Get visibility into Shadow AI7 steps
  7. Respond to a compromised AI agent9 steps
  8. Evaluate an AI SOC or agentic triage tool7 steps
  9. Prepare for AI-powered attackers5 steps

Stories

  1. Attacks on AI Breach The Hacker News High

    OpenRouter Drops 3 Providers After Researchers Catch Months of Prompt Theft at AI Hosting Firms

    Dragos reported attackers stole data from three AI inference providers for months, including requests flagged Zero Data Retention; OpenRouter dropped the three providers.

    ReviewReview data retention settings and provider routing used with AI inference gateways

    LLM02 #ai-infrastructure#data-theft#llm-gateway Brief In your stack
  2. Attacks on AI Vulnerability The Hacker News Medium

    A Single Malicious Webpage Let Researchers Hijack Meta Muse and Access Private Chats

    Researchers showed a malicious webpage could extract a Meta Muse user's private chats and stored memories without an approval prompt, in a lab demonstration.

    ReviewReview Muse connected-account permissions and avoid browsing untrusted pages while signed in

    LLM01LLM02 #prompt-injection#ai-assistant#data-exposure Brief In your stack
  3. Defensive AI Tooling The Decoder Medium

    Signal blocks screenshots on iOS 27 and Android to stop AI agents from reading private chats

    Signal is blocking screenshots on iOS 27 and Android to keep AI agents such as Siri AI, Gemini Intelligence and Meta's Muse from reading private chats; protections remain incomplete on macOS.

    MitigateEnable Signal's screenshot blocking and note macOS protections remain incomplete

    AML.T0086ASI02 #signal#privacy#ai-agents 2 sources Brief In your stack
  4. Defensive AI AI security The Decoder Medium

    OpenAI makes it much harder for attackers to extract how its latest AI models think

    OpenAI strengthened safeguards against extracting internal reasoning from GPT-6.2 Astra and GPT-6.2 Sol and is suspending accounts tied to distillation campaigns.

    AML.T0024 #llm#distillation#model-security 1 min read Brief In your stack
  5. Defensive AI Policy CyberScoop Medium

    Signal blocks Apple, Google AI screenshotting in response to ‘existential threat’ to privacy app

    Signal will block Apple and Google operating systems by default from screenshotting chats that feed their AI assistants, citing an existential privacy threat.

    MitigateEnable Signal's screenshot blocking setting and review AI assistant access to messaging apps

    AML.T0086 #signal#privacy#ai-agents 2 min read Brief In your stack
  6. Attacks on AI Policy The Record Medium

    US companies’ use of Chinese open weight AI draws rebuke from House chairmen

    House Homeland Security Committee chairmen criticized U.S. companies for using lower-cost Chinese open weight AI models in certain projects.

    ReviewReview use of Chinese open weight models in existing projects

    #open-weight#china#congress Brief In your stack
  7. Attacks on AI AI security NVD (AI keyword search) Medium

    CVE-2026-77329: Tapo MCP server DNS rebinding allows unauthenticated device control when no API key is set

    Tapo, a set of Rust and Python APIs and an MCP server for TP-Link Tapo smart devices, versions 0.3.1 through 0.5.0 skip Host or Origin validation in its Streamable HTTP implementation.

    PatchUpgrade the tapo-mcp server to version 0.5.0 or later.

    CVE-2026-77329 Brief In your stack
  8. Attacks on AI AI security NVD (AI keyword search) Medium

    CVE-2026-134293: SQL injection in SurrealDB 3.1.0 MCP server identifier validation

    SurrealDB versions 3.1.0 before 4.0.0 contain an SQL injection flaw in the Model Context Protocol (MCP) server.

    ReviewIdentify SurrealDB deployments running version 3.1.0 through 3.x and confirm whether the MCP server component is enabled

    CVE-2026-134293 Brief In your stack
  9. Attacks on AI AI security NVD (AI keyword search) Medium

    CVE-2026-114494: codebase-memory-mcp before 0.9.0 stack overflow via Cypher query_graph projections

    codebase-memory-mcp provides local code intelligence for developers and AI agents through MCP tools.

    PatchUpgrade codebase-memory-mcp to version 0.9.0 or later.

    CVE-2026-114494 Brief In your stack
  10. Attacks on AI AI security NVD (AI keyword search) Medium

    CVE-2026-77383: mcp-ssh-manager shell injection in ssh_db_* tools before 3.6.7

    mcp-ssh-manager is an MCP server for managing servers over SSH.

    PatchUpgrade mcp-ssh-manager to version 3.6.7 or later.

    CVE-2026-77383 Brief In your stack
  11. Attacks on AI AI security NVD (AI keyword search) Medium

    mcp-ssh-manager prior to 3.8.5: shell command injection in SSH backup tools (CVE-2026-129995)

    mcp-ssh-manager is an MCP server for managing servers over SSH.

    PatchUpgrade mcp-ssh-manager to version 3.8.5 or later on all MCP server hosts.

    CVE-2026-129995 Brief In your stack
  12. Offensive AI Malware The Hacker News Medium

    Bazuka Android Malware Uses Fake Screen Overlays to Hide Credential Theft and Device Control

    Bazuka Android Malware Uses Fake Screen Overlays to Hide Credential Theft and Device Control

    In your stack
  13. Attacks on AI AI security NVD (AI keyword search)

    CVE-2026-114495: codebase-memory-mcp heap overflow via crafted .codebase-memory artifact (fixed in 0.9.0)

    codebase-memory-mcp versions prior to 0.9.0 mishandle the original_size value in a repository's .codebase-memory/ artifact.json during automatic import.

    PatchUpgrade codebase-memory-mcp to version 0.9.0 or later on all developer workstations and agent hosts.

    CVE-2026-114495 Brief In your stack
  14. Attacks on AI AI security NVD (AI keyword search)

    CVE-2026-54032: LibreChat before 0.8.6 XSS via remote MCP description and banner message

    LibreChat versions prior to 0.8.6 render remote MCP server description values through dangerouslySetInnerHTML without sanitization.

    PatchUpgrade LibreChat to version 0.8.6 or later.

    CVE-2026-54032 Brief In your stack
  15. Attacks on AI AI security NVD (AI keyword search)

    codebase-memory-mcp before 0.9.0: detect_changes base_branch argument enables arbitrary file write via git option injection

    codebase-memory-mcp provides local code intelligence through MCP tools.

    PatchUpgrade codebase-memory-mcp to version 0.9.0 or later.

    CVE-2026-114496 Brief In your stack
  16. Attacks on AI AI security NVD (AI keyword search)

    CVE-2026-114499: codebase-memory-mcp .gitignore matcher ReDoS-style stall before 0.10.0

    codebase-memory-mcp versions prior to 0.10.0 have a .gitignore matcher that implements * and ** through recursive backtracking without a work bound.

    PatchUpgrade codebase-memory-mcp to version 0.10.0 or later.

    CVE-2026-114499 Brief In your stack
  17. Attacks on AI AI security NVD (AI keyword search)

    CVE-2026-114497: codebase-memory-mcp Windows graph UI process-kill route lacks ownership check

    codebase-memory-mcp versions before 0.9.1-rc.1 have a flaw in the optional graph UI's POST /api/process-kill route.

    PatchUpgrade codebase-memory-mcp to 0.9.1-rc.1 or later on all Windows hosts.

    CVE-2026-114497 Brief In your stack

One-line summaries and suggested actions are AI-assisted. Read the source before acting.

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.