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 1527 results — Medium severityCVE-2026-72749n8n: prototype pollution DoS via Edit Fields node6.50.6%n8nAug 11MEDICVE-2026-72785Craft CMS: read-only role can restructure categories4.30.3%—Aug 11MEDIECVE-2026-14549Ray Enterprise Translation WP plugin: broken access control4.30.3%Ray Enterprise TranslationAug 11MEDIECVE-2026-14548Ray Translation WP: Subscribers can hijack API token6.50.3%Ray Enterprise TranslationAug 11MEDICVE-2026-18942Feast operator: code injection escalates to cluster admin5.50.4%rhoai/odh-pipeline-runtime-tensorflow-cuda-py312-rhel9Aug 10MEDIECVE-2026-12570Keras: OOM DoS via malicious .keras model load5.50.2%kerasAug 10MEDICVE-2026-19334Ollama-mcp: command injection via model args5.31.1%—Aug 9MEDICVE-2026-54338JupyterHub: unauth log flooding via long usernames5.30.4%jupyterhubAug 7MEDICVE-2026-12261NLTK: downloader cross-package poisoning of models5.30.2%—Aug 7MEDIGHSA-xxpx-f366-4xpqCraft CMS: view-only role can restructure categories——craftcms/cmsAug 6MEDICVE-2026-71433LangGraph Checkpoint: prefix match leaks cross-tenant data5.30.4%langgraph-checkpoint-sqliteAug 6MEDICVE-2025-9266Non-AI false positive: WordPress theme, not ML Accelerate4.30.3%AccelerateAug 6MEDIECVE-2026-19008openclaw-cn: symlink escape bypasses agent sandbox6.30.4%—Aug 6MEDIECVE-2026-19007openclaw-cn: broken privilege check on elevated senders6.30.4%—Aug 6MEDIECVE-2026-19006openclaw-cn: auth bypass in bash exec approval gate6.30.4%—Aug 6MEDICVE-2026-66885Livebook: CSRF binds victim session to attacker6.50.2%—Aug 5MEDIECVE-2026-18959InnoShop: path traversal in file manager deletes files5.40.5%—Aug 5MEDICVE-2026-7869Langflow: path traversal allows arbitrary file write5.40.3%langflowAug 5MEDICVE-2026-7658Langflow: username path traversal enables data destruction6.50.5%langflowAug 5MEDICVE-2026-10128Langflow: built-in component leaks server env vars6.50.3%langflowAug 5Frequently 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