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 4307 resultsCVE-2026-111057Mercury: regex blocklist bypass allows unauthenticated RCE10.00.7%mercuryOct 19HIGHCVE-2026-112304docTR: unsafe torch.load deserialization enables RCE7.50.4%—Oct 19HIGHECVE-2026-112264BentoML: Dockerfile injection via docker.env keys7.80.2%bentomlOct 19MEDIECVE-2026-112107fastllm: safetensors offset overflow enables memory corruption6.30.3%—Oct 19MEDIECVE-2026-112080Llama-Chinese: code injection via adapter config loader6.30.4%—Oct 19MEDIECVE-2026-111991YOLOv9: code injection via ONNX metadata names/stride6.30.4%—Oct 18HIGHECVE-2026-111990Hospital Mgmt System: SQL injection in appointment cancel7.30.3%—Oct 18MEDIECVE-2026-111987A1111 WebUI: stored XSS via safetensors metadata hash4.30.4%—Oct 18MEDICVE-2026-111985stable-diffusion-webui: safetensors header DoS via memory4.30.4%—Oct 18HIGHCVE-2026-59970Tandoor Recipes: SSRF via AI provider URL exposes internal network7.70.3%litellmOct 16CRITCVE-2026-105192LMCache: unauthenticated RCE via pickle in ZMQ transport9.81.0%vllmOct 16CRITCVE-2026-96620Claude Agent SDK: argument injection enables RCE—0.7%claude-agent-sdk-pythonOct 16LOWCVE-2026-76894ckan-mcp-server: missing postMessage origin checks in UI3.10.2%@aborruso/ckan-mcp-serverOct 16MEDICVE-2026-85977libtirpc: unbounded PMAP reply decoding causes client DoS5.3—rhoai/odh-mlflow-rhel9Oct 16MEDICVE-2026-85231libtirpc: unbounded memory allocation causes RPC DoS6.5—rhoai/odh-mlflow-rhel9Oct 16HIGHECVE-2026-111702ChatOllama: IDOR exposes other users' knowledge bases7.50.4%chat-ollamaOct 16CRITECVE-2026-111693DataBuff APM: hard-coded admin credentials allow full takeover9.80.5%—Oct 16CRITECVE-2026-111692DataBuff ai-apm-web: hardcoded JWT secret enables admin bypass9.80.6%—Oct 16HIGHCVE-2026-111671Cube-studio: IDOR lets users disrupt others' services7.10.3%—Oct 16CRITCVE-2026-94603Podman: checkpoint images override sandbox on run10.00.5%github.com/containers/podmanOct 15Frequently 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