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 1961 results — Active exploitationCVE-2026-70626NLTK: symlink escape allows arbitrary file read6.20.2%nltkSep 8MEDIECVE-2026-86289Ollama: integer overflow in GGUF decoder causes DoS4.30.7%ollamaSep 7HIGHECVE-2026-86177Pterodactyl Panel: subuser escalation to console RCE8.80.6%—Sep 5HIGHECVE-2026-72794SiYuan: CookieKey leak enables session forgery8.60.3%github.com/siyuan-note/siyuan/kernelSep 4HIGHECVE-2026-75911CodeWhale: repo config silently enables shell RCE7.80.2%codewhaleSep 4HIGHECVE-2026-75912DeepSeek-TUI: git_blame argument injection leaks files7.40.4%codewhaleSep 4HIGHECVE-2026-75856deepseek-tui: SSRF via DNS-pinning TOCTOU bypass8.60.5%codewhaleSep 4HIGHECVE-2026-75915deepseek-tui: js_execution leaks parent secrets to LLM7.50.7%codewhaleSep 4HIGHECVE-2026-75857CodeWhale: shell approval bypass via interactive tool7.00.2%codewhaleSep 4HIGHECVE-2026-75859CodeWhale: arbitrary file read via instructions field7.50.5%codewhaleSep 4HIGHECVE-2026-75914CodeWhale: symlink traversal leaks files via vision API7.50.5%codewhaleSep 4HIGHECVE-2026-85686ms-swift: unauth SSRF via multimodal media URLs7.50.5%ms-swiftSep 4HIGHECVE-2026-85673LLaMA-Factory: SSRF guard bypass via redirect/DNS rebind7.50.5%llama-factorySep 4MEDIECVE-2026-85670tokenizers: malformed vocab crashes process (DoS)6.50.5%tokenizersSep 4HIGHECVE-2026-85666OGX/Llama Stack: SSRF via MCP tool server_url7.50.7%llama-stackSep 4MEDIECVE-2026-85578SiYuan: auth bypass leaks hidden notebook files6.50.4%—Sep 4MEDIECVE-2026-72800SiYuan: broken authz leaks DB schema & block IDs5.80.3%github.com/siyuan-note/siyuan/kernelSep 3MEDIECVE-2026-72805SiYuan: auth bypass exposes private notebook content5.80.3%github.com/siyuan-note/siyuan/kernelSep 3HIGHECVE-2026-72810SiYuan: WebSocket leak bypasses publish access control8.60.5%github.com/siyuan-note/siyuan/kernelSep 3MEDIECVE-2026-72812SiYuan: broken auth on refreshBacklink enables DoS6.50.4%github.com/siyuan-note/siyuan/kernelSep 3Frequently 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