AI Security Threat Feed
Latest CVEs affecting AI/ML systems, updated continuously. Tracked from NVD, GitHub Advisory, and CISA KEV.
AI/ML CVEs Tracked
Critical
New This Week
In CISA KEV
Latest AI Security Threats
Showing 20 of 199 results — High severity, has patchLangChain: deserialization poisons LLM chat history
CVE-2026-44843 Open WebUI: path traversal + file upload leads to RCE
CVE-2026-44566 Open WebUI: auth bypass gives pending users full LLM access
CVE-2026-44567 open-webui: XSS via XLSX preview enables session hijack
CVE-2026-44549 banks: SSTI enables RCE via unsandboxed Jinja2 templates
CVE-2026-44209 open-webui: RAG poisoning via unauthorized KB overwrite
CVE-2026-44554 open-webui: auth bypass allows unrestricted model access
CVE-2026-44556 open-webui: access control bypass via model chaining
CVE-2026-44555 open-webui: Redis cache poisoning enables cross-instance tool hijack
CVE-2026-44552 open-webui: stale Socket.IO role allows cross-user note R/W
CVE-2026-44553 open-webui: XSS in model descriptions steals session tokens
CVE-2026-44721 n8n-mcp: path traversal + SSRF exposes n8n API keys
GHSA-8g7g-hmwm-6rv2 diffusers: trust_remote_code bypass enables silent RCE
CVE-2026-44513 diffusers: silent RCE via None.py trust_remote_code bypass
GHSA-j7w6-vpvq-j3gm Aegra: cross-tenant IDOR hijacks user thread data
CVE-2026-44504 praisonai: RCE via unpatched tool_override exec_module
CVE-2026-44334 praisonaiagents: SSRF via URL parser confusion bypass
CVE-2026-44335 GitPython: git config injection enables hook RCE
CVE-2026-44244 JupyterLab: one-click RCE via notebook HTML cell output
CVE-2026-42557 mistune: ReDoS exposes Jupyter/AI services to DoS
CVE-2026-33079 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
AI Threat Alert