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 patchGHSA-763v-5pjm-fx36Strands Agents: world-readable session files in /tmp——strands-agentsOct 27HIGHGHSA-g5ff-637f-6q2mLiteLLM: file read via vertex_ai_credentials alias8.1—litellmOct 27MEDIGHSA-hhww-mrg2-969hLiteLLM: reflected XSS in SSO debug callback6.8—litellmOct 27MEDICVE-2026-60083SiYuan: MCP file tool leaks publish-share passwords4.90.4%github.com/siyuan-note/siyuan/kernelOct 27CRITCVE-2026-48705MONAI: NaN/inf DICOM input causes DoS and corrupt inference9.30.5%monaiOct 27HIGHECVE-2026-115924Rembg: unauthenticated path traversal leaks files8.60.4%rembgOct 26MEDICVE-2026-115922ONNX: unbounded alloc in 2/4-bit unpack causes DoS6.20.1%onnxOct 26MEDICVE-2026-115921ONNX: null deref/oversized alloc in Scan inference DoS6.20.1%onnxOct 26MEDICVE-2026-115920ONNX: ConvTranspose shape inference crash causes DoS6.20.2%onnxOct 26MEDICVE-2026-115919ONNX: OOB read in RNN shape inference crashes app6.20.2%onnxOct 26MEDICVE-2026-115918vLLM: chat template bypass enables DoS via /v1/responses6.50.4%vllmOct 26LOWCVE-2026-115917vLLM: wildcard CORS lets web pages reach local servers3.40.2%vllmOct 26MEDICVE-2026-115916vLLM: off-by-one token ID check crashes engine (DoS)6.50.3%vllmOct 26MEDICVE-2026-115913vLLM: Phi-4 audio attention causes GPU OOM DoS6.50.3%vllmOct 26HIGHCVE-2026-115912vLLM: pickle deserialization RCE via multimodal cache7.50.5%vllmOct 26MEDICVE-2026-115911vLLM: chat template DoS via unbounded Jinja rendering6.50.3%vllmOct 26HIGHCVE-2026-115915vLLM: image decoder abuse enables RCE/DoS8.10.7%vllmOct 26MEDICVE-2026-115914vLLM: zero-sum OCR image crashes engine (DoS)6.50.4%vllmOct 26MEDICVE-2026-112937filelock: rename-to-rmtree deletes other users' dirs6.10.2%filelockOct 23LOWCVE-2026-112913filelock: Windows side-file planting breaks ReadWriteLock3.30.1%filelockOct 23Frequently 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