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.
- 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 827 results — has patch CVE-2026-39891 praisonai: SSTI enables RCE via agent instructions 8.8 0.6% praisonai Apr 8 HIGH CVE-2026-39889 PraisonAI: unauth A2U stream leaks all agent activity 7.5 0.4% praisonai Apr 8 CRIT CVE-2026-39888 praisonaiagents: sandbox escape enables host RCE 10.0 0.5% praisonaiagents Apr 8 CRIT E CVE-2026-39890 PraisonAI: YAML deserialization enables unauthenticated RCE 9.8 0.6% praisonai Apr 8 MEDI E CVE-2026-39411 LobeChat: auth bypass via forged XOR obfuscated header 5.0 0.1% @lobehub/lobehub Apr 8 HIGH GHSA-69x8-hrgq-fjj8 LiteLLM: auth bypass chain enables full privilege escalation — — litellm Apr 8 HIGH GHSA-89gg-p5r5-q6r4 MONAI: pickle deserialization RCE in Auto3DSeg 7.7 — monai Apr 7 MEDI GHSA-83f3-hh45-vfw9 OpenClaw: cleartext WebSocket exposes gateway credentials — — openclaw Apr 7 MEDI GHSA-jj6q-rrrf-h66h openclaw: timing side-channel leaks shared-secret length — — openclaw Apr 7 MEDI GHSA-rxmx-g7hr-8mx4 OpenClaw: Zalo webhook dedup collision silently drops events — — openclaw Apr 7 MEDI GHSA-fh32-73r9-rgh5 OpenClaw: CDP host bypass exposes localhost browser state — — openclaw Apr 7 MEDI GHSA-w6wx-jq6j-6mcj openclaw: script swap bypasses pnpm dlx approval — — openclaw Apr 7 MEDI GHSA-98ch-45wp-ch47 OpenClaw: approval bypass via env key normalization gap — — openclaw Apr 7 MEDI GHSA-2f7j-rp58-mr42 OpenClaw: info disclosure exposes host filesystem paths — — openclaw Apr 7 MEDI GHSA-2qrv-rc5x-2g2h OpenClaw: untrusted plugin RCE via workspace channel setup — — openclaw Apr 7 MEDI GHSA-5hff-46vh-rxmw OpenClaw: read-only scope bypass kills agent sessions — — openclaw Apr 7 MEDI GHSA-4p4f-fc8q-84m3 openclaw: iOS bridge bypass enables unauthorized agent runs — — openclaw Apr 7 MEDI GHSA-846p-hgpv-vphc OpenClaw: path traversal → host file exfiltration via QQ Bot — — openclaw Apr 7 MEDI GHSA-m34q-h93w-vg5x openclaw: path traversal enables remote dir overwrite — — openclaw Apr 7 LOW GHSA-fqrj-m88p-qf3v OpenClaw: cross-account webhook event suppression — — openclaw Apr 7 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