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 2876 results — no patchCVE-2026-103908AMP for WP: arbitrary shortcode execution by auth users5.4—AMP for WP – Accelerated Mobile PagesNov 6MEDICVE-2026-123291JetBrains Datalore: IDOR exposes other workspaces' notebooks4.3——Nov 6MEDICVE-2026-123290JetBrains Datalore: hidden notebook code exposed unauthenticated5.3——Nov 6MEDICVE-2026-123289JetBrains Datalore: improper authorization lets viewers edit files5.4——Nov 6MEDICVE-2026-123288JetBrains Datalore: stored XSS in notebook charts5.4——Nov 6MEDICVE-2026-123287JetBrains Datalore: unauthenticated download of private notebooks5.9—jupyterNov 6MEDICVE-2026-123286JetBrains Datalore: improper authz exposes storage token5.9——Nov 6HIGHCVE-2026-123281JetBrains Datalore: argument injection allows sidecar command execution7.5——Nov 6CRITCVE-2026-123279JetBrains Datalore: view-only users can run notebook code9.0——Nov 6HIGHCVE-2026-113663AG2: shell filter bypass via newline enables RCE8.8—autogenNov 5HIGHCVE-2026-110930Codex Desktop Windows: argument injection runs code8.0—Codex Desktop for WindowsNov 5HIGHCVE-2026-102739ESPectre: unsafe NPZ pickle load allows code execution7.8——Nov 5UNKNCVE-2026-70660stable-diffusion.cpp: OOB read via crafted safetensors———Nov 5HIGHCVE-2026-55368H2O: access-log buffer overflow crashes HTTP server8.10.3%—Nov 4HIGHCVE-2026-55367H2O: unbounded CONNECT-UDP capsule buffering causes DoS7.50.3%h2oNov 4MEDICVE-2026-122015npcpy: improper input validation in MLX provider6.30.3%mlxNov 4HIGHCVE-2026-122135Mistral Vibe: RCE via repo-configured gpg.program8.80.5%mistral-vibeNov 4HIGHCVE-2026-122134Mistral Vibe: Git filter RCE on repo open8.80.5%mistral-vibeNov 4HIGHCVE-2026-122133Mistral Vibe: untrusted git.exe path allows RCE on Windows8.80.4%mistral-vibeNov 4UNKNCVE-2026-121008SQL::Abstract::Tree: XSS via unescaped html profile output—0.2%—Nov 4Frequently 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