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 2346 results — no patch CVE-2026-18621 OpenShift AI Pipelines: confused deputy grants node-root 7.6 0.4% rhaiis/vllm-cpu-rhel9 Aug 10 HIGH E CVE-2026-69112 Accelerate: path traversal in checkpoint loading 7.1 0.1% accelerate Aug 10 HIGH E CVE-2026-71962 Flowise: auth bypass leaks private chatflow files 7.5 0.7% flowise Aug 10 UNKN CVE-2026-72751 CTI-Transmute: stored XSS in graph UI via Pivotick — 0.3% — Aug 10 HIGH CVE-2026-72692 OpenSignServer: missing authz forges document declines 7.5 0.3% — Aug 10 LOW E CVE-2026-14211 Booking Calendar: IDOR exposes any customer's PII 3.8 0.2% — Aug 10 MEDI CVE-2026-19334 Ollama-mcp: command injection via model args 5.3 0.6% — Aug 9 UNKN E CVE-2026-10595 lollms: path traversal enables unauth file read — 0.5% parisneo/lollms Aug 9 HIGH E CVE-2026-67620 Flowise: SSRF bypass exposes cloud metadata credentials 7.7 0.3% flowise Aug 8 HIGH CVE-2026-64636 Plesk Obsidian: authenticated SQLi exposes panel DB 7.7 0.3% — Aug 7 HIGH E CVE-2026-70636 Flowise: auth bypass triggers unauthorized OAuth refresh 7.5 0.5% Flowise Aug 6 CRIT E CVE-2026-67622 Flowise: IDOR in Assistants API leaks OpenAI credentials 9.9 0.3% Flowise Aug 6 HIGH E CVE-2026-67621 Flowise: broken authz lets viewers poison RAG stores 7.6 0.3% Flowise Aug 6 HIGH CVE-2026-43632 llama.cpp: UAF race in tokenize endpoints risks RCE 8.1 0.3% — Aug 6 MEDI CVE-2025-9266 Non-AI false positive: WordPress theme, not ML Accelerate 4.3 0.2% Accelerate Aug 6 HIGH CVE-2026-57819 Apache CXF: JAX-RS form parameter flood enables DoS 7.5 0.5% — Aug 6 MEDI E CVE-2026-19008 openclaw-cn: symlink escape bypasses agent sandbox 6.3 0.3% — Aug 6 MEDI E CVE-2026-19007 openclaw-cn: broken privilege check on elevated senders 6.3 0.2% — Aug 6 MEDI E CVE-2026-19006 openclaw-cn: auth bypass in bash exec approval gate 6.3 0.2% — Aug 6 HIGH E CVE-2026-69111 Milvus: unauthenticated DoS via /management/stop 7.5 0.6% milvus Aug 5 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