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 1550 results — no patch CVE-2026-48166 Filament: timing side-channel exposes registered emails 5.3 — — Jun 22 HIGH CVE-2026-48505 Filament: MFA race condition enables recovery code reuse 7.4 — — Jun 22 MEDI CVE-2026-56357 n8n: webhook forgery enables unauthorized workflow execution 4.0 — n8n Jun 22 CRIT CVE-2026-56348 n8n: SSRF bypasses allowlist, exfiltrates credentials 9.1 — n8n Jun 22 HIGH CVE-2026-56268 Flowise: cross-workspace chatflow config disclosure 7.7 — Flowise Jun 22 MEDI CVE-2026-55443 LangChain: path traversal exposes files outside agent root 5.1 — langchain Jun 22 UNKN CVE-2026-12479 Keras: path traversal via layer names allows arbitrary file write — — keras-team/keras Jun 22 HIGH CVE-2026-10845 WebSphere AS: JAX-WS auth bypass, unauthorized access 7.3 — — Jun 22 HIGH CVE-2026-56104 Chainlit: session hijacking via WebSocket restoration 8.2 — chainlit Jun 22 CRIT CVE-2026-10561 Langflow: auth bypass + unauthenticated RCE (CVSS 10) 10.0 — langflow Jun 22 CRIT CVE-2026-7664 Langflow: auth bypass in MCP endpoint, CVSS 9.8 9.8 — Langflow OSS Jun 22 HIGH CVE-2026-9029 Grafana: stored XSS in geomap bypasses CVE-2023-0507 fix 7.3 — — Jun 22 MEDI CVE-2026-12822 Langflow: code injection via Bundle URL Loader (PoC) 5.3 — langflow Jun 21 MEDI CVE-2026-12821 Flowise: path traversal in S3 loader exposes documents 6.3 — Flowise Jun 21 MEDI CVE-2026-56393 Craft CMS: stored XSS hijacks admin panel sessions 4.8 — — Jun 21 HIGH E CVE-2025-71378 picklescan: detection bypass enables RCE via pickle files 8.1 — picklescan Jun 21 HIGH E CVE-2025-71357 picklescan: detection bypass enables RCE via malicious models 8.1 — picklescan Jun 21 HIGH E CVE-2025-71351 picklescan: scanner bypass enables RCE via pickle files — — picklescan Jun 21 HIGH E CVE-2025-71348 picklescan: scanner bypass enables supply chain RCE 8.1 — picklescan Jun 21 MEDI CVE-2026-12799 litellm: authorization bypass exposes user list 4.3 — litellm Jun 21 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