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 4330 resultsCVE-2026-44223vLLM: speculative decoding DoS via penalty params6.50.4%vllmMay 6HIGHCVE-2026-42557JupyterLab: one-click RCE via notebook HTML cell output8.80.5%notebookMay 6HIGHCVE-2026-44118OpenClaw: owner spoofing via bearer token header7.80.1%OpenClawMay 6MEDICVE-2026-44117OpenClaw: SSRF in QQBot media upload bypasses URL checks5.80.2%OpenClawMay 6HIGHCVE-2026-44116OpenClaw: SSRF in Zalo sendPhoto exposes internal resources8.60.3%OpenClawMay 6HIGHCVE-2026-44115OpenClaw: heredoc shell expansion bypasses exec allowlist8.80.4%OpenClawMay 6HIGHCVE-2026-44114OpenClaw: dotenv namespace override enables runtime hijack7.80.1%OpenClawMay 6HIGHCVE-2026-44113OpenClaw: TOCTOU symlink race escapes sandbox mount7.70.2%OpenClawMay 6CRITCVE-2026-44112OpenClaw: TOCTOU symlink race escapes OpenShell sandbox9.67.3%OpenClawMay 6HIGHECVE-2026-33079mistune: ReDoS exposes Jupyter/AI services to DoS7.50.6%mistuneMay 6LOWECVE-2026-8026Flowise: info disclosure via login API response handler3.70.3%flowiseMay 6MEDIECVE-2026-44222vLLM: token injection DoS via multimodal placeholders6.50.4%vllmMay 5HIGHCVE-2026-42266JupyterLab: Extension allow-list bypass enables privesc8.85.7%jupyterlabMay 5MEDIECVE-2026-43901wireshark-mcp: path traversal enables arbitrary file write via MCP6.80.3%—May 5HIGHECVE-2026-42079PPTAgent: eval injection enables RCE via LLM prompt injection8.60.1%pptagentMay 5HIGHGHSA-cwj3-vqpp-pmxropenclaw: Model bypasses authz to persist unsafe config8.8—openclawMay 5HIGHGHSA-r39h-4c2p-3jxpOpenClaw: RCE via malicious repo setup-api.js7.8—openclawMay 5MEDIGHSA-q8ff-7ffm-m3r9openclaw: stale webhook secret survives credential rotation6.0—openclawMay 5CRITECVE-2026-42048Langflow: path traversal allows arbitrary directory deletion9.64.2%langflowMay 5MEDICVE-2026-40864JupyterHub: CSRF bypass on spawn and share endpoints5.40.1%jupyterhubMay 5Frequently 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