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 resultsONNX: hardlink path traversal leaks sensitive files
CVE-2026-34446ONNX: property overwrite via crafted model file
CVE-2026-34445OpenClaw: UNC/file URL bypass in Windows media loaders
CVE-2026-34510ONNX: symlink path traversal allows arbitrary file read
CVE-2026-27489Anthropic SDK: TOCTOU symlink escape in async memory tool
CVE-2026-34452anthropic-ai/sdk: memory tool path traversal escape
CVE-2026-34451anthropic-sdk: insecure file perms expose agent memory
CVE-2026-34450Claude Setup: DLL search-order hijacking LPE
CVE-2026-22561MLflow: command injection via model_uri in mlserver mode
CVE-2026-0596OpenClaw: SSRF in fal provider exposes internal services
CVE-2026-34504OpenClaw: WebSocket session persists after token revocation
CVE-2026-34503OpenClaw: sandbox bypass enables arbitrary file read
CVE-2026-33581OpenClaw: webhook brute-force enables event forgery
CVE-2026-33580OpenClaw: scope bypass escalates low-priv to admin
CVE-2026-33579OpenClaw: allowlist bypass exposes AI agents to all users
CVE-2026-33578OpenClaw: scope bypass lets low-priv ops elevate node access
CVE-2026-33577OpenClaw: pre-auth media fetch enables disk exhaustion DoS
CVE-2026-33576OpenClaw: auth bypass lets any Teams user invoke AI agent
CVE-2026-34506OpenClaw: webhook rate-limit bypass enables brute-force
CVE-2026-34505OpenClaw: sandbox escape via fs-bridge TOCTOU race
CVE-2026-32988Frequently 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