AI Threat Alert
AI 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 3035 results GHSA-4jpm-cgx2-8h37 Flowise: unauth API exposes plaintext API keys and tokens — — flowise Apr 16 HIGH GHSA-48m6-ch88-55mj Flowise: Mass Assignment allows cross-tenant org takeover 8.1 — flowise Apr 16 CRIT GHSA-9wc7-mj3f-74xv Flowise CSVAgent: RCE via Python code injection — — flowise-components Apr 16 HIGH GHSA-f228-chmx-v6j6 Flowise: prompt injection RCE via AirtableAgent 8.3 — flowise-components Apr 16 MEDI GHSA-9hrv-gvrv-6gf2 Flowise: SSRF bypass enables cloud metadata access — — flowise-components Apr 16 MEDI GHSA-qqvm-66q4-vf5c Flowise: SSRF bypass enables cloud credential theft — — flowise-components Apr 16 MEDI GHSA-w6v6-49gh-mc9w Flowise: path traversal allows arbitrary file write via vector store — — flowise-components Apr 16 MEDI GHSA-m7mq-85xj-9x33 Flowise: hardcoded default key enables JWT token forgery 5.6 — flowise Apr 16 MEDI GHSA-2qqc-p94c-hxwh Flowise: hardcoded session secret enables auth bypass 5.6 — flowise Apr 16 MEDI GHSA-cc4f-hjpj-g9p8 Flowise: hardcoded JWT defaults enable full auth bypass 5.6 — flowise Apr 16 MEDI GHSA-6pcv-j4jx-m4vx Flowise: unauthenticated SSO config exposes OAuth secrets 5.3 — flowise Apr 16 LOW GHSA-gj9q-8w99-mp8j openclaw: TOCTOU race bypasses exec script preflight — — openclaw Apr 16 CRIT E CVE-2026-40933 Flowise: RCE via MCP stdio command injection 9.9 13.4% flowise-components Apr 16 HIGH CVE-2026-30617 LangChain-ChatChat: RCE via unauthenticated MCP interface 8.6 0.5% — Apr 15 CRIT E CVE-2025-61260 OpenAI Codex CLI: RCE via malicious MCP config files 9.8 6.6% @openai/codex Apr 14 HIGH GHSA-p4h8-56qp-hpgv mcp-ssh: argument injection enables LLM-driven local RCE — — — Apr 14 HIGH E CVE-2026-1462 Keras: safe_mode bypass allows RCE via model deserialization 8.8 0.4% keras Apr 13 HIGH GHSA-75hx-xj24-mqrw n8n-mcp: unauthenticated HTTP endpoints enable DoS + recon 8.2 — n8n-mcp Apr 10 MEDI E CVE-2026-40190 langsmith: prototype pollution enables auth bypass, RCE 5.6 0.3% langsmith Apr 10 MEDI E CVE-2026-40086 rembg: path traversal exposes arbitrary files via HTTP API 5.3 0.6% rembg Apr 10 Frequently 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