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 1074 results — Active exploitation CVE-2025-6638 HuggingFace Transformers: ReDoS in MarianTokenizer 7.5 0.5% transformers Sep 12 HIGH E CVE-2025-10156 Picklescan: CRC bypass hides malicious pickle in ZIP 7.5 1.4% picklescan Sep 10 HIGH E CVE-2025-10157 PickleScan: subclass bypass enables malicious model RCE 8.3 0.8% picklescan Sep 10 HIGH E CVE-2025-58757 MONAI: unsafe pickle deserialization RCE in data pipeline 8.8 0.6% monai Sep 9 HIGH E CVE-2025-58756 MONAI: unsafe deserialization in CheckpointLoader allows RCE 8.8 0.7% monai Sep 9 HIGH E CVE-2025-58755 MONAI: path traversal allows arbitrary file write 8.8 0.6% monai Sep 9 HIGH E CVE-2025-56265 n8n: unrestricted file upload RCE via Chat Trigger 8.8 0.6% n8n Sep 8 MEDI E CVE-2025-58446 xgrammar: DoS via oversized JSON schema grammar parsing — 0.5% xgrammar Sep 5 HIGH E CVE-2025-6984 EverNoteLoader: XXE exposes host files in LangChain 7.5 1.5% langchain-community Sep 4 CRIT E CVE-2025-55526 n8n-workflows: path traversal in download_workflow endpoint 9.1 0.8% fastapi Aug 26 HIGH E CVE-2025-5302 llama-index: JSON parsing DoS via deep recursion 8.6 0.3% llama-index-core Aug 26 HIGH E CVE-2025-57809 xgrammar: uncontrolled recursion in grammar parsing causes DoS 7.5 0.4% xgrammar Aug 25 HIGH E CVE-2025-57760 Langflow: privilege escalation to full superuser via CLI 8.8 0.4% langflow Aug 25 HIGH E CVE-2025-48956 vLLM: unauthenticated DoS via oversized HTTP header 7.5 0.5% vllm Aug 21 HIGH E CVE-2025-8747 Keras: safe mode bypass enables RCE via model load 7.8 0.1% keras Aug 11 HIGH E CVE-2025-54886 skops: joblib fallback enables RCE via model load 8.4 0.2% skops Aug 8 MEDI E CVE-2025-54952 ExecuTorch: integer overflow enables RCE via model loading — 0.6% executorch Aug 8 CRIT E CVE-2025-54950 ExecuTorch: OOB read in model loader enables RCE 9.8 0.6% executorch Aug 8 CRIT E CVE-2025-53767 Azure OpenAI: SSRF EoP, no auth required (CVSS 10) 10.0 1.0% azure_openai Aug 7 MEDI E CVE-2025-44779 Ollama: arbitrary file deletion via /api/pull 6.6 0.2% ollama Aug 7 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