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-2026-44244 GitPython: git config injection enables hook RCE 7.8 0.2% GitPython May 6 MEDI E CVE-2026-44223 vLLM: speculative decoding DoS via penalty params 6.5 0.4% vllm May 6 HIGH CVE-2026-42557 JupyterLab: one-click RCE via notebook HTML cell output — 0.3% notebook May 6 HIGH E CVE-2026-33079 mistune: ReDoS exposes Jupyter/AI services to DoS — 0.3% mistune May 6 MEDI CVE-2026-44222 vLLM: token injection DoS via multimodal placeholders 6.5 0.4% vllm May 5 HIGH CVE-2026-42266 JupyterLab: Extension allow-list bypass enables privesc 8.8 0.5% jupyterlab May 5 HIGH E CVE-2026-42079 PPTAgent: eval injection enables RCE via LLM prompt injection 8.6 0.1% pptagent May 5 HIGH GHSA-cwj3-vqpp-pmxr openclaw: Model bypasses authz to persist unsafe config 8.8 — openclaw May 5 HIGH GHSA-r39h-4c2p-3jxp OpenClaw: RCE via malicious repo setup-api.js 7.8 — openclaw May 5 MEDI GHSA-q8ff-7ffm-m3r9 openclaw: stale webhook secret survives credential rotation 6.0 — openclaw May 5 CRIT E CVE-2026-42048 Langflow: path traversal allows arbitrary directory deletion 9.6 4.4% langflow May 5 MEDI CVE-2026-40864 JupyterHub: CSRF bypass on spawn and share endpoints 5.4 0.2% jupyterhub May 5 MEDI CVE-2026-40934 jupyter-server: auth cookie survives password reset 6.8 0.3% jupyter-server May 5 HIGH CVE-2026-40110 Jupyter Server: CORS bypass via regex anchor omission — 0.4% jupyter-server May 5 HIGH E CVE-2026-35397 Jupyter Server: path traversal leaks sibling directories 7.1 0.5% jupyter-server May 5 MEDI E CVE-2025-61669 jupyter-server: Open redirect enables credential phishing — 0.3% jupyter-server May 5 MEDI CVE-2026-43570 OpenClaw: symlink traversal exposes host filesystem 6.5 0.3% openclaw May 5 MEDI GHSA-93rg-2xm5-2p9v openclaw: auth bypass exposes Gateway bootstrap config — — openclaw May 4 MEDI GHSA-5h3g-6xhh-rg6p openclaw: TOCTOU race allows out-of-sandbox file read — — openclaw May 4 HIGH GHSA-wppj-c6mr-83jj openclaw: TOCTOU sandbox escape via symlink swap — — openclaw May 4 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