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-2025-12360Better: security flaw enables exploitation4.30.2%—Nov 6MEDIECVE-2025-12695dspy: security flaw enables exploitation5.90.3%dspyNov 4MEDIECVE-2025-12058Keras: safe_mode bypass enables file read and SSRF—0.2%kerasOct 29MEDIECVE-2025-11844smolagents: security flaw enables exploitation5.40.3%smolagentsOct 22MEDIECVE-2025-60511Moodle: IDOR enables unauthorized data access4.30.2%—Oct 21MEDICVE-2025-61620vllm: DoS via Jinja template injection in chat API6.50.2%vllmOct 7MEDIECVE-2025-8917clearml: path traversal in safe_extract → RCE risk5.80.5%clearmlOct 5MEDIECVE-2025-55556TensorFlow: non-deterministic compilation breaks Embedding6.50.2%tensorflowSep 25MEDIECVE-2025-55554PyTorch: integer overflow in nan_to_num causes DoS5.30.3%pytorchSep 25MEDICVE-2025-46153PyTorch: Dropout inconsistency enables membership inference5.30.4%pytorchSep 25MEDICVE-2025-46152PyTorch: OOB write causes incorrect bitwise shift results5.30.5%pytorchSep 25MEDICVE-2025-46150PyTorch: torch.compile silent output inconsistency5.30.4%pytorchSep 25MEDICVE-2025-46149PyTorch: reachable assertion in nn.Fold with inductor5.30.4%pytorchSep 25MEDICVE-2025-46148PyTorch: PairwiseDistance silent miscalculation, integrity risk5.30.4%pytorchSep 25MEDICVE-2025-58177n8n: stored XSS in LangChain chat trigger (public)5.40.2%n8nSep 15MEDIECVE-2025-6051Transformers: ReDoS in EnglishNormalizer exhausts CPU5.30.4%transformersSep 14MEDIECVE-2025-58446xgrammar: DoS via oversized JSON schema grammar parsing—0.6%xgrammarSep 5MEDIGHSA-q77w-mwjj-7mqxpicklescan: scanner bypass enables model RCE——picklescanAug 26MEDIGHSA-49gj-c84q-6qm9picklescan: scanner bypass enables RCE via ML model files——picklescanAug 26MEDIGHSA-9w88-8rmg-7g2ppicklescan: scan bypass allows silent RCE via ML models——picklescanAug 26Frequently 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