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 910 results — Active exploitationPraisonAI: SSRF via api_base steals cloud IAM credentials
CVE-2026-34936 PraisonAI: OS command injection via run_python() shell escape
CVE-2026-34937 praisonaiagents: sandbox bypass enables full host RCE
CVE-2026-34938 Open WebUI: access control bypass leaks Tool Valve API keys
CVE-2026-34222 ONNX: symlink traversal reads host files via model loading
CVE-2026-34447 ONNX: symlink path traversal allows arbitrary file read
CVE-2026-27489 MLflow: command injection via model_uri in mlserver mode
CVE-2026-0596 awesome-llm-apps MCP Agent: cross-session credential theft
CVE-2026-29872 CrewAI: RCE via Docker fallback in CodeInterpreter
CVE-2026-2275 MLflow: RCE via unsanitized model dependency specs
CVE-2025-15379 MLflow: path traversal enables sandbox escape, file overwrite
CVE-2025-15036 OpenUI: hard-coded LiteLLM master key credential leak
CVE-2026-4993 langchain-core: path traversal exposes host secrets via prompt config
CVE-2026-34070 @mobilenext/mobile-mcp: path traversal via AI agent tool
CVE-2026-33989 smolagents: code injection via incomplete sandbox fix
CVE-2026-4963 MLflow: broken access control exposes experiment traces
CVE-2025-15381 Open WebUI: IDOR exposes AI memories and private files
CVE-2026-29071 open-webui: missing authz allows cross-KB file deletion
CVE-2026-29070 Open WebUI: BOLA enables RAG poisoning via file overwrite
CVE-2026-28788 Open WebUI: path traversal leaks server filesystem path
CVE-2026-28786 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