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 1908 results — High severityGHSA-7437-7hg8-frrwOpenClaw: env var injection enables host RCE——openclawApr 9HIGHGHSA-jf56-mccx-5f3fOpenClaw: wake hook trust violation elevates to System prompt——openclawApr 9HIGHGHSA-gfmx-pph7-g46xopenclaw: trust boundary bypass enables prompt injection——openclawApr 9HIGHGHSA-4ggg-h7ph-26qrn8n-mcp: authenticated SSRF leaks cloud metadata8.5—n8n-mcpApr 8HIGHECVE-2026-39891praisonai: SSTI enables RCE via agent instructions8.80.6%praisonaiApr 8HIGHCVE-2026-39889PraisonAI: unauth A2U stream leaks all agent activity7.50.4%praisonaiApr 8HIGHCVE-2026-3357Langflow: deserialization RCE via FAISS component default8.80.5%langflowApr 8HIGHGHSA-69x8-hrgq-fjj8LiteLLM: auth bypass chain enables full privilege escalation——litellmApr 8HIGHGHSA-89gg-p5r5-q6r4MONAI: pickle deserialization RCE in Auto3DSeg7.7—monaiApr 7HIGHGHSA-vfw7-6rhc-6xxgopenclaw: env var injection via workspace config——openclawApr 7HIGHECVE-2026-22682OpenHarness: file tool permission bypass leaks files7.10.1%—Apr 7HIGHECVE-2026-35485text-generation-webui: unauthenticated path traversal file read7.50.7%gradioApr 7HIGHECVE-2026-39308PraisonAI: recipe registry path traversal file write7.10.3%PraisonAIApr 6HIGHECVE-2026-39306PraisonAI: recipe path traversal allows arbitrary file write7.30.3%PraisonAIApr 6HIGHECVE-2026-39307PraisonAI: Zip Slip enables arbitrary file write / RCE8.10.3%PraisonAIApr 6HIGHECVE-2026-35021Claude Code CLI: shell injection enables RCE7.80.0%—Apr 6HIGHECVE-2026-35020Claude Code CLI: OS command injection via TERMINAL env8.40.1%claude-codeApr 6HIGHECVE-2026-34940KubeAI: RCE via shell injection in Ollama startup probe8.80.5%—Apr 6HIGHCVE-2026-34511OpenClaw: PKCE verifier leak enables OAuth token theft5.30.2%openclawApr 4HIGHECVE-2026-35394mobile-mcp: intent injection enables device control via AI agent8.30.4%@mobilenext/mobile-mcpApr 4Frequently 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