AI Threat Alert

AI Security Threat Feed

Latest CVEs affecting AI/ML systems — LLM frameworks, ML libraries, AI agents, vector databases, and inference servers. Vulnerabilities are tracked from NVD, GitHub Advisory, CISA KEV, MITRE ATLAS, and enriched with CVSS, EPSS, exploitation confidence, AI-component classification, and compliance mappings to ISO 42001, EU AI Act, NIST AI RMF, and OWASP LLM Top 10. Updated continuously as new CVEs are published.

Sources
Each CVE is enriched with
  • CVSS severity
  • EPSS exploit probability
  • Exploitation confidence
  • AI-component classification
  • Compliance mappings
4,307

AI/ML CVEs Tracked

533

Critical

95

New This Week

25

In CISA KEV

Sort:DateCVSSEPSSKEV firstMost exploited
Filter:AllCriticalHighMediumKEV onlyActive exploitationHas patchNo patch

Latest AI Security Threats

Showing 20 of 4307 results
SeverityCVE IDSummaryCVSSEPSSPackageDate
MEDIGHSA-j8f7-x8jm-wmm4Langflow: SSRF in built-in components exposes cloud metadata——lfx-doclingOct 6MEDIECVE-2026-105775vLLM: OOB read in Mamba2 mixer enables remote DoS4.30.3%vLLMOct 6HIGHECVE-2026-102826simple-git: command injection via git clone config bypass8.10.5%—Oct 5MEDICVE-2026-105758vLLM: unbounded video frame decoding enables DoS5.30.3%vllmOct 5MEDICVE-2026-105760vLLM: unbounded video frame options enable DoS5.30.3%vllmOct 5MEDICVE-2026-105754vLLM: input validation flaws let attacker crash EngineCore6.50.3%vllmOct 5MEDICVE-2026-105757vLLM: unhandled structured-output errors crash engine (DoS)6.50.3%vllmOct 5MEDICVE-2026-105755vLLM: request-ID cache key collision corrupts rerank scores4.20.2%vllmOct 5MEDICVE-2026-105756vLLM: unvalidated cache_salt crashes EngineCore (DoS)6.50.3%vllmOct 5MEDIGHSA-g7fw-3gjp-g5hfOpenClaw channels: allowlist bypass exposes chat reads6.5—openclawOct 5HIGHECVE-2026-100722vm2: unhandled Promise rejection in construct trap kills host8.60.3%vm2Oct 5HIGHECVE-2026-105786Joplin Server: app-auth flaw enables account takeover—0.4%—Oct 5HIGHECVE-2026-105759vLLM: unbounded metrics labels allow memory-exhaustion DoS7.50.4%vllmOct 5MEDICVE-2026-105753vLLM: reachable assertion in cache causes DoS6.50.4%vllmOct 5LOWCVE-2026-105752vLLM: cache_salt dropped on tool continuations leaks prefixes3.10.2%vllmOct 5MEDIECVE-2026-105785Joplin Server: reset-token reuse enables account takeover4.80.2%—Oct 5MEDIECVE-2026-105784Joplin: CSS injection via jsoncanvas note rendering4.60.2%—Oct 5HIGHECVE-2026-105783Joplin: Web Clipper CORS flaw leaks permanent API token8.00.1%—Oct 5HIGHECVE-2026-104851fsspec: Jinja2 SSTI in Kerchunk refs allows RCE8.80.5%fsspecOct 5HIGHECVE-2026-92954vm2: unhandled host Promise rejection crashes Node host8.60.5%vm2Oct 5

Frequently asked questions

What is an AI security threat feed?

An AI security threat feed is a continuously updated stream of vulnerabilities (CVEs) affecting AI and machine-learning systems — LLM frameworks, ML libraries, AI agents, vector databases, and inference servers — filtered out of the broader CVE firehose and enriched for relevance.

Which sources are the AI CVEs tracked from?

CVEs are tracked from NVD, GitHub Advisory, CISA KEV, and MITRE ATLAS, then enriched with CVSS, EPSS, exploitation confidence, AI-component classification, and compliance mappings.

What AI systems do these vulnerabilities affect?

Coverage spans LLM frameworks, ML libraries, AI agents, vector databases, and inference servers — the components most security teams now run in production.

How often is the AI threat feed updated?

The feed updates continuously as new CVEs are published and enriched, so the most recent AI/ML vulnerabilities appear at the top.

Is the AI security feed free?

Yes — the public feed is free to browse. A Pro subscription adds breaking alerts, MITRE ATLAS mappings, compliance reports (ISO 42001, EU AI Act), and full CISO analysis.

Need deeper analysis?

Get ATLAS technique mappings, compliance reports (ISO 42001, EU AI Act), breaking alerts, and full CISO analysis with a Pro subscription.

Start 14-Day Free Trial