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 851 results — Medium severity CVE-2026-34755 vLLM: OOM DoS via unbounded video frame decoding 6.5 0.3% vllm Apr 3 MEDI CVE-2026-34753 vLLM: SSRF in batch API exposes cloud metadata endpoints 5.4 0.2% vllm Apr 3 MEDI CVE-2026-34052 ltiauthenticator: OAuth nonce leak causes server DoS 5.9 0.3% jupyterhub-ltiauthenticator Apr 3 MEDI CVE-2026-33709 JupyterHub: open redirect enables post-login phishing — 0.2% jupyterhub Apr 3 MEDI CVE-2026-34756 vLLM: DoS via unbounded n parameter causes OOM crash 6.5 0.3% vllm Apr 3 MEDI GHSA-9q7v-8mr7-g23p OpenClaw: SSRF in marketplace fetch hits internal AI infra — — openclaw Apr 2 MEDI E CVE-2026-34447 ONNX: symlink traversal reads host files via model loading 5.5 0.2% onnx Apr 1 MEDI CVE-2026-34446 ONNX: hardlink path traversal leaks sensitive files 4.7 0.2% onnx Apr 1 MEDI CVE-2026-34452 Anthropic SDK: TOCTOU symlink escape in async memory tool — 0.1% anthropic Mar 31 MEDI CVE-2026-34451 anthropic-ai/sdk: memory tool path traversal escape — 0.3% @anthropic-ai/sdk Mar 31 MEDI CVE-2026-34450 anthropic-sdk: insecure file perms expose agent memory — 0.1% anthropic Mar 31 MEDI CVE-2026-33581 OpenClaw: sandbox bypass enables arbitrary file read 6.5 0.6% OpenClaw Mar 31 MEDI CVE-2026-33580 OpenClaw: webhook brute-force enables event forgery 6.5 0.4% OpenClaw Mar 31 MEDI CVE-2026-33578 OpenClaw: allowlist bypass exposes AI agents to all users 4.3 0.3% OpenClaw Mar 31 MEDI CVE-2026-33576 OpenClaw: pre-auth media fetch enables disk exhaustion DoS 6.5 0.4% OpenClaw Mar 31 MEDI CVE-2026-34506 OpenClaw: auth bypass lets any Teams user invoke AI agent 4.3 0.3% OpenClaw Mar 31 MEDI CVE-2026-34505 OpenClaw: webhook rate-limit bypass enables brute-force 6.5 0.3% OpenClaw Mar 31 MEDI CVE-2026-32977 OpenClaw: TOCTOU race condition enables sandbox file escape 6.3 0.1% OpenClaw Mar 31 MEDI CVE-2026-32976 OpenClaw: auth bypass mutates protected agent config 6.5 0.2% OpenClaw Mar 31 MEDI CVE-2026-32921 OpenClaw: script approval bypass allows code execution 6.3 0.2% OpenClaw Mar 31 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