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 patchCVE-2025-5302llama-index: JSON parsing DoS via deep recursion8.60.3%llama-index-coreAug 26HIGHECVE-2025-57809xgrammar: uncontrolled recursion in grammar parsing causes DoS7.50.5%xgrammarAug 25MEDIGHSA-vv6j-3g6g-2pvjpicklescan: PyTorch gadget bypasses scanner, enables RCE——picklescanAug 22MEDIGHSA-vr7h-p6mm-wpmhpicklescan: PyTorch gadget bypasses pickle RCE detection——picklescanAug 22MEDIGHSA-h3qp-7fh3-f8h4picklescan: detection bypass via PyTorch proxy RCE——picklescanAug 22MEDIGHSA-f745-w6jp-hpxxpicklescan: RCE bypass via torch.utils.collect_env——picklescanAug 22MEDIGHSA-f4x7-rfwp-v3xwpicklescan: scanner bypass enables RCE via PyTorch function——picklescanAug 22MEDIGHSA-86cj-95qr-2p4fpicklescan: detection bypass enables PyTorch model RCE——picklescanAug 22MEDIGHSA-4r9r-ch6f-vxmxpicklescan: PyTorch bypass allows undetected RCE——picklescanAug 22HIGHCVE-2025-9141vLLM: RCE via eval() in Qwen3 Coder tool parser8.84.0%vllmAug 21HIGHGHSA-9gvj-pp9x-gcfrpicklescan: detection bypass allows malicious pickle exec——picklescanAug 12HIGHECVE-2025-54886skops: joblib fallback enables RCE via model load8.40.2%skopsAug 8CRITCVE-2025-54951ExecuTorch: heap buffer overflow RCE in model loading9.80.7%executorchAug 8CRITCVE-2025-30404ExecuTorch: integer overflow RCE on model load9.80.6%executorchAug 8CRITCVE-2025-30405ExecuTorch: integer overflow in model load → RCE9.80.6%executorchAug 8CRITCVE-2025-54949ExecuTorch: heap buffer overflow RCE via model loading9.80.7%executorchAug 8CRITECVE-2025-54950ExecuTorch: OOB read in model loader enables RCE9.80.6%executorchAug 8HIGHECVE-2025-54413skops: RCE via MethodNode unsafe deserialization—0.2%skopsJul 26HIGHECVE-2025-54412skops: OperatorFuncNode type confusion → RCE—0.2%skopsJul 26HIGHCVE-2025-30402ExecuTorch: heap overflow in method load, RCE risk8.10.4%executorchJul 11Frequently 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