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 533 results — Critical severityCVE-2026-37004LiteLLM: unauth SSTI in /prompts/test enables RCE9.80.8%litellmAug 27CRITECVE-2025-61165Cohere North AI: file upload flaw enables RCE9.80.4%—Aug 26CRITECVE-2025-61163Cohere North AI: missing Origin check enables CSWSH9.80.4%—Aug 26CRITECVE-2026-45018Chainlit: unauth RCE via MCP stdio cmd injection9.81.1%chainlitAug 25CRITECVE-2026-55536PraisonAI: WebSocket auth bypass hijacks browser agent9.10.5%PraisonAIAug 25CRITCVE-2026-71914DrayTek VigorAP: pre-auth UDP command injection to root9.82.6%—Aug 24CRITECVE-2026-61539Xinference: eval() on LLM output enables RCE10.01.2%xinferenceAug 21CRITCVE-2026-77776Headroom LLM proxy: IDOR exposes cross-user memory9.10.6%—Aug 21CRITECVE-2026-55445Qinglong panel: unauth admin credential reset bypass—0.5%@whyour/qinglongAug 20CRITECVE-2026-76850LMDeploy: RCE via unauth pickle deserialization9.81.3%lmdeployAug 19CRITECVE-2026-62988Froxlor: API leaks password hashes & TOTP seeds9.00.6%froxlor/froxlorAug 18CRITECVE-2026-75913CodeWhale: git_show argument injection enables file write9.30.5%codewhaleAug 18CRITCVE-2026-64849MLflow: unauth SSRF via webhook hits cloud metadata9.310.0%mlflowAug 17CRITECVE-2026-72811SiYuan: SQL injection enables cross-notebook DB access10.00.4%github.com/siyuan-note/siyuan/kernelAug 14CRITCVE-2026-19297Langflow: missing login rate limiting enables account takeover9.10.6%langflowAug 13CRITECVE-2026-73601Flowise: RCE via Custom MCP node env var injection—1.1%FlowiseAug 13CRITECVE-2026-73487Flowise: Python sandbox bypass enables unauth RCE—1.0%FlowiseAug 13CRITCVE-2026-73485Flowise: RCE via Airtable Agent pyodide sandbox bypass—0.6%FlowiseAug 13CRITECVE-2026-73483Flowise: sandbox escape via puppeteer.launch() to RCE—0.6%FlowiseAug 13CRITCVE-2026-72765n8n: expression sandbox escape leads to RCE9.90.9%n8nAug 11Frequently 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