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 366 results — Active exploitation, has patchamplify-codegen-ui: eval injection enables build-time RCE
CVE-2025-4318 Flyto2 Core: SSRF via unvalidated URLs in agent tools
CVE-2026-67428 Flyto2 Core: SSRF leaks LLM API keys via base_url
CVE-2026-67425 Quarkus: HTTP auth bypass via %3B/%2F path smuggling
CVE-2026-50559 Pterodactyl Wings: JWT reuse enables file upload bypass
CVE-2026-54593 Pterodactyl Panel: global rate limiter enables panel-wide login DoS
CVE-2026-61609 Gitea: cached permission check allows repo takeover
CVE-2026-27775 Pillow: OOB read/DoS via unchecked mmap stride (McIdas)
CVE-2026-54058 ViewComponent: stale context leaks admin UI cross-user
CVE-2026-54497 SiYuan Note: chrome-extension origin auth bypass
CVE-2026-54069 SiYuan: /assets path traversal exposes API secrets
CVE-2026-54066 Open WebUI: encoded path traversal in terminal proxy
CVE-2026-59221 Open WebUI: channel IDOR leaks tool-server API keys
CVE-2026-59222 Open WebUI: IDOR leaks private channel/DM threads
CVE-2026-59215 Open WebUI: cache leak exposes cross-user model lists
CVE-2026-59213 Open WebUI: read-only users can inject files into RAG KBs
CVE-2026-59217 Open WebUI: session hijack enables cross-user code exec
CVE-2026-59216 Open WebUI: revoked JWTs bypass WebSocket auth
CVE-2026-59219 Open WebUI: unauth Socket.IO bypass alters doc state
CVE-2026-59715 Open WebUI: ReDoS in skill mentions blocks event loop
CVE-2026-59220 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