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 1431 results — has patchllama-index: JSON parsing DoS via deep recursion
CVE-2025-5302xgrammar: uncontrolled recursion in grammar parsing causes DoS
CVE-2025-57809picklescan: PyTorch gadget bypasses scanner, enables RCE
GHSA-vv6j-3g6g-2pvjpicklescan: PyTorch gadget bypasses pickle RCE detection
GHSA-vr7h-p6mm-wpmhpicklescan: detection bypass via PyTorch proxy RCE
GHSA-h3qp-7fh3-f8h4picklescan: RCE bypass via torch.utils.collect_env
GHSA-f745-w6jp-hpxxpicklescan: scanner bypass enables RCE via PyTorch function
GHSA-f4x7-rfwp-v3xwpicklescan: detection bypass enables PyTorch model RCE
GHSA-86cj-95qr-2p4fpicklescan: PyTorch bypass allows undetected RCE
GHSA-4r9r-ch6f-vxmxvLLM: RCE via eval() in Qwen3 Coder tool parser
CVE-2025-9141picklescan: detection bypass allows malicious pickle exec
GHSA-9gvj-pp9x-gcfrskops: joblib fallback enables RCE via model load
CVE-2025-54886ExecuTorch: heap buffer overflow RCE in model loading
CVE-2025-54951ExecuTorch: heap buffer overflow RCE via model loading
CVE-2025-54949ExecuTorch: OOB read in model loader enables RCE
CVE-2025-54950ExecuTorch: integer overflow in model load → RCE
CVE-2025-30405ExecuTorch: integer overflow RCE on model load
CVE-2025-30404skops: RCE via MethodNode unsafe deserialization
CVE-2025-54413skops: OperatorFuncNode type confusion → RCE
CVE-2025-54412ExecuTorch: heap overflow in method load, RCE risk
CVE-2025-30402Frequently 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