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 1527 results — Medium severityCVE-2026-34753vLLM: SSRF in batch API exposes cloud metadata endpoints5.40.3%vllmApr 3MEDICVE-2026-34052ltiauthenticator: OAuth nonce leak causes server DoS5.90.3%jupyterhub-ltiauthenticatorApr 3MEDICVE-2026-33709JupyterHub: open redirect enables post-login phishing—0.2%jupyterhubApr 3MEDICVE-2026-34756vLLM: DoS via unbounded n parameter causes OOM crash6.50.4%vllmApr 3MEDIGHSA-9q7v-8mr7-g23pOpenClaw: SSRF in marketplace fetch hits internal AI infra——openclawApr 2MEDIECVE-2026-34447ONNX: symlink traversal reads host files via model loading5.50.3%onnxApr 1MEDICVE-2026-34446ONNX: hardlink path traversal leaks sensitive files4.70.2%onnxApr 1MEDICVE-2026-34510OpenClaw: UNC/file URL bypass in Windows media loaders5.30.3%OpenClawApr 1MEDICVE-2026-34452Anthropic SDK: TOCTOU symlink escape in async memory tool—0.1%anthropicMar 31MEDICVE-2026-34451anthropic-ai/sdk: memory tool path traversal escape—0.4%@anthropic-ai/sdkMar 31MEDICVE-2026-34450anthropic-sdk: insecure file perms expose agent memory—0.1%anthropicMar 31MEDICVE-2026-33581OpenClaw: sandbox bypass enables arbitrary file read6.50.6%OpenClawMar 31MEDICVE-2026-33580OpenClaw: webhook brute-force enables event forgery6.50.4%OpenClawMar 31MEDICVE-2026-33578OpenClaw: allowlist bypass exposes AI agents to all users4.30.3%OpenClawMar 31MEDICVE-2026-33576OpenClaw: pre-auth media fetch enables disk exhaustion DoS6.50.4%OpenClawMar 31MEDICVE-2026-34506OpenClaw: auth bypass lets any Teams user invoke AI agent4.30.3%OpenClawMar 31MEDICVE-2026-34505OpenClaw: webhook rate-limit bypass enables brute-force6.50.3%OpenClawMar 31MEDICVE-2026-32977OpenClaw: TOCTOU race condition enables sandbox file escape6.30.1%OpenClawMar 31MEDICVE-2026-32976OpenClaw: auth bypass mutates protected agent config6.50.2%OpenClawMar 31MEDICVE-2026-32921OpenClaw: script approval bypass allows code execution6.30.2%OpenClawMar 31Frequently 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