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 485 results — High severity, no patchmcp-ssh: argument injection enables LLM-driven local RCE
GHSA-p4h8-56qp-hpgv LiteLLM: RCE via bytecode rewriting in guardrails API
CVE-2026-40217 PraisonAI: unauth WebSocket drains OpenAI API credits
CVE-2026-40116 PraisonAI: arg injection injects env vars into Cloud Run
CVE-2026-40113 n8n-MCP: SSRF exposes cloud metadata via MCP headers
CVE-2026-39974 Langflow: deserialization RCE via FAISS component default
CVE-2026-3357 text-generation-webui: unauthenticated path traversal file read
CVE-2026-35485 Claude Code CLI: shell injection enables RCE
CVE-2026-35021 Claude Code CLI: OS command injection via TERMINAL env
CVE-2026-35020 mobile-mcp: intent injection enables device control via AI agent
CVE-2026-35394 oauthenticator: auth bypass enables JupyterHub account takeover
CVE-2026-33175 Ajenti: missing authz lets any user install packages
CVE-2026-35175 awesome-llm-apps MCP Agent: cross-session credential theft
CVE-2026-29872 @mobilenext/mobile-mcp: path traversal via AI agent tool
CVE-2026-33989 MLflow: broken access control exposes experiment traces
CVE-2025-15381 langflow: Access Control bypass enables privilege escalation
CVE-2026-33484 langflow: IDOR enables unauthorized data access
CVE-2026-33053 nltk: Path Traversal enables file access
CVE-2026-33236 deepdiff: DoS causes service disruption
CVE-2026-33155 Flowise: header spoof auth bypass exposes admin API & creds
CVE-2026-30820 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