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-2026-44550open-webui: mass assignment enables cross-user folder injection5.00.3%open-webuiMay 8MEDIECVE-2026-40610BentoML: symlink traversal exfiltrates host secrets at build5.50.3%bentomlMay 7MEDIGHSA-cqmh-pcgr-q42f@axonflow/openclaw: credential exposure via insecure file permissions5.5—@axonflow/openclawMay 6MEDIECVE-2026-44223vLLM: speculative decoding DoS via penalty params6.50.4%vllmMay 6MEDICVE-2026-44117OpenClaw: SSRF in QQBot media upload bypasses URL checks5.80.2%OpenClawMay 6MEDIECVE-2026-44222vLLM: token injection DoS via multimodal placeholders6.50.4%vllmMay 5MEDIECVE-2026-43901wireshark-mcp: path traversal enables arbitrary file write via MCP6.80.3%—May 5MEDIGHSA-q8ff-7ffm-m3r9openclaw: stale webhook secret survives credential rotation6.0—openclawMay 5MEDICVE-2026-40864JupyterHub: CSRF bypass on spawn and share endpoints5.40.1%jupyterhubMay 5MEDIECVE-2026-42045LobeChat: XSS-to-RCE via exposed Electron IPC6.20.3%@lobehub/lobehubMay 5MEDIECVE-2026-40934jupyter-server: auth cookie survives password reset6.80.3%jupyter-serverMay 5MEDIECVE-2025-61669jupyter-server: Open redirect enables credential phishing—0.2%jupyter-serverMay 5MEDIECVE-2026-7844Langchain-Chatchat: auth bypass on file service endpoints6.30.3%—May 5MEDICVE-2026-43570OpenClaw: symlink traversal exposes host filesystem6.50.3%openclawMay 5MEDIGHSA-93rg-2xm5-2p9vopenclaw: auth bypass exposes Gateway bootstrap config——openclawMay 4MEDIGHSA-5h3g-6xhh-rg6popenclaw: TOCTOU race allows out-of-sandbox file read——openclawMay 4MEDIGHSA-x3h8-jrgh-p8jxOpenClaw: exec allowlist bypass allows hidden shell code——openclawMay 4MEDIGHSA-55cf-xx38-4p9pOpenClaw: .env injection redirects connector endpoints——openclawMay 4MEDIGHSA-q3jj-46pq-826ropenclaw: ACP child session security envelope bypass——openclawMay 4MEDIGHSA-2hh7-c75g-qj2ropenclaw: SSRF bypass via Zalo plugin photo URLs——openclawMay 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