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 2900 results — no patchCVE-2026-22176OpenClaw: cmd injection in Windows task script generation6.10.7%OpenClawMar 19HIGHECVE-2026-33155deepdiff: DoS causes service disruption—0.5%—Mar 18CRITECVE-2026-28500onnx: Integrity Verification bypass enables tampering9.10.3%onnxMar 18MEDICVE-2026-27545OpenClaw: symlink race bypasses agent run approval6.10.1%OpenClawMar 18MEDICVE-2026-27524OpenClaw: prototype pollution bypasses command gate4.30.3%OpenClawMar 18MEDICVE-2026-27523OpenClaw: sandbox path traversal bypasses bind isolation6.10.3%OpenClawMar 18MEDICVE-2026-27522OpenClaw: path traversal enables arbitrary file read via media actions6.50.4%OpenClawMar 18MEDICVE-2026-22217OpenClaw: $SHELL env hijack enables arbitrary code execution6.10.1%OpenClawMar 18HIGHCVE-2026-22181OpenClaw: SSRF guard bypass exposes internal services7.60.2%OpenClawMar 18MEDICVE-2026-22180OpenClaw: path traversal enables arbitrary file writes5.30.1%OpenClawMar 18HIGHECVE-2026-22179OpenClaw: allowlist bypass enables arbitrary OS command exec7.20.7%OpenClawMar 18MEDICVE-2026-22178OpenClaw: ReDoS via Feishu mention metadata6.50.3%OpenClawMar 18HIGHCVE-2026-22175OpenClaw: allowlist bypass lets agents run any command7.10.4%OpenClawMar 18MEDICVE-2026-22174OpenClaw: local token leak via CDP probe hijack6.80.1%OpenClawMar 18HIGHCVE-2026-22171OpenClaw: path traversal allows arbitrary file write8.20.4%OpenClawMar 18MEDICVE-2026-22170OpenClaw: empty allowlist bypasses BlueBubbles DM auth6.50.3%OpenClawMar 18MEDICVE-2026-22169OpenClaw: safeBins allowlist bypass enables command exec6.70.2%OpenClawMar 18MEDICVE-2026-22168OpenClaw: cmd.exe argument smuggling evades approval log6.50.4%OpenClawMar 18UNKNCVE-2026-25083GROWI: Missing Auth allows unauthorized operations—0.3%—Mar 16HIGHECVE-2026-4111libarchive: infinite loop DoS in RAR5 decompression7.50.7%rhaiis/vllm-cuda-rhel9Mar 13Frequently 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