AI Threat AlertAI 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.
- CVSS severity
- EPSS exploit probability
- Exploitation confidence
- AI-component classification
- Compliance mappings
AI/ML CVEs Tracked
Critical
New This Week
In CISA KEV
Latest AI Security Threats
Showing 20 of 1527 results — Medium severityGHSA-qqq7-4hxc-x63copenclaw: local file exfiltration via trusted MEDIA refs——openclawApr 9MEDIGHSA-q2gc-xjqw-qp89OpenClaw: eval approval bypass enables unintended code exec——openclawApr 9MEDIECVE-2026-4878libcap: TOCTOU race in cap_set_file() enables privesc6.70.2%rhaiis/vllm-spyre-rhel9Apr 9MEDIGHSA-926x-3r5x-gfhwLangChain: f-string template injection exposes object internals5.3—langchain-coreApr 8MEDICVE-2026-40037OpenClaw: request body replay leaks credentials via redirect6.50.3%OpenClawApr 8MEDIECVE-2026-5803openai-realtime-ui: SSRF in API proxy endpoint6.30.2%—Apr 8MEDIGHSA-766v-q9x3-g744praisonaiagents: agent context leak + path traversal6.5—praisonaiagentsApr 8MEDIECVE-2026-39411LobeChat: auth bypass via forged XOR obfuscated header5.00.1%@lobehub/lobehubApr 8MEDIECVE-2026-1163lollms: sessions persist after password reset4.10.2%lollmsApr 8MEDICVE-2026-39398openclaw-claude-bridge: sandbox bypass exposes CLI tools——claude-codeApr 8MEDIGHSA-83f3-hh45-vfw9OpenClaw: cleartext WebSocket exposes gateway credentials——openclawApr 7MEDIGHSA-jj6q-rrrf-h66hopenclaw: timing side-channel leaks shared-secret length——openclawApr 7MEDIGHSA-rxmx-g7hr-8mx4OpenClaw: Zalo webhook dedup collision silently drops events——openclawApr 7MEDIGHSA-fh32-73r9-rgh5OpenClaw: CDP host bypass exposes localhost browser state——openclawApr 7MEDIGHSA-w6wx-jq6j-6mcjopenclaw: script swap bypasses pnpm dlx approval——openclawApr 7MEDIGHSA-98ch-45wp-ch47OpenClaw: approval bypass via env key normalization gap——openclawApr 7MEDIGHSA-2f7j-rp58-mr42OpenClaw: info disclosure exposes host filesystem paths——openclawApr 7MEDIGHSA-2qrv-rc5x-2g2hOpenClaw: untrusted plugin RCE via workspace channel setup——openclawApr 7MEDIGHSA-5hff-46vh-rxmwOpenClaw: read-only scope bypass kills agent sessions——openclawApr 7MEDIGHSA-4p4f-fc8q-84m3openclaw: iOS bridge bypass enables unauthorized agent runs——openclawApr 7Frequently 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