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
4,330

AI/ML CVEs Tracked

535

Critical

107

New This Week

25

In CISA KEV

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

Latest AI Security Threats

Showing 20 of 4330 results
SeverityCVE IDSummaryCVSSEPSSPackageDate
HIGHCVE-2026-62205OpenClaw: auth bypass in MS Teams message actions7.10.4%openclawJul 17HIGHCVE-2026-62203OpenClaw: env var filter gap enables priv escalation8.80.5%openclawJul 17HIGHCVE-2026-62202OpenClaw: cron isolation flaw regains denied tools8.80.5%openclawJul 17HIGHCVE-2026-62201OpenClaw: exec-server bypass allows internal SSRF7.70.4%openclawJul 17HIGHCVE-2026-54340H2O: HTTP/2 HPACK amplification enables DoS7.50.5%h2oJul 16HIGHCVE-2026-44453h2o: alloca stack overflow crashes server on request7.50.5%—Jul 16MEDICVE-2026-44452h2o HTTP server: NULL SNI crash causes DoS5.90.4%—Jul 16HIGHCVE-2026-44436Quicly: QUIC DoS via oversized Connection ID overflow7.50.5%—Jul 16HIGHCVE-2026-44435H2O/Quicly: unauthenticated QUIC DoS via assertion crash7.50.5%—Jul 16MEDICVE-2026-44434Quicly/H2O: on-path attacker can force QUIC resets5.30.2%—Jul 16HIGHCVE-2026-44433Quicly/H2O: QUIC flow-control bug enables memory exhaustion DoS7.50.5%—Jul 16HIGHECVE-2026-63086TGI: SSRF via image_url exposes cloud metadata creds8.60.4%text-generation-inferenceJul 16MEDICVE-2026-47751Claude Code Action: RCE via malicious PR .mcp.json config—0.8%claude-code-actionJul 16MEDICVE-2026-55407Buffa: protobuf decoder DoS via 22x memory amplification—0.8%buffaJul 16MEDICVE-2026-55406buffa: use-after-free in Rust protobuf OwnedView type—0.2%buffaJul 16MEDICVE-2026-15610WPBot: auth bypass burns AI API credits via RAG4.30.4%wpbotJul 16MEDICVE-2026-15106WPBot: broken auth lets attackers wipe chat logs5.30.5%wpbotJul 16HIGHCVE-2026-23538Feast: unauth WebSocket connections cause DoS7.50.9%rhoai/odh-workbench-jupyter-datascience-cpu-py312-rhel9Jul 16MEDIECVE-2026-54497ViewComponent: stale context leaks admin UI cross-user6.80.3%view_componentJul 15CRITECVE-2026-54458AVideo: stored XSS in YPTSocket enables admin takeover9.60.4%—Jul 15

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