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 1625 resultsPraisonAI: recipe path traversal allows arbitrary file write
CVE-2026-39306 PraisonAI: path traversal enables arbitrary file write/RCE
CVE-2026-39305 PraisonAI: Zip Slip enables arbitrary file write / RCE
CVE-2026-39307 OpenClaw: script preflight bypass enables unsafe exec
CVE-2026-34425 Claude Code: OS command injection, credential theft
CVE-2026-35022 Claude Code CLI: shell injection enables RCE
CVE-2026-35021 Claude Code CLI: OS command injection via TERMINAL env
CVE-2026-35020 kedro-datasets: path traversal enables arbitrary file write
CVE-2026-35492 KubeAI: RCE via shell injection in Ollama startup probe
CVE-2026-34940 Ollama: SSRF in Model Pull API enables network pivot
CVE-2026-5530 OpenClaw: PKCE verifier leak enables OAuth token theft
CVE-2026-34511 Directus: cleartext storage exposes AI API keys
GHSA-mvv8-v4jj-g47j Budibase: Unauthenticated RCE as root via webhook
CVE-2026-35216 mobile-mcp: intent injection enables device control via AI agent
CVE-2026-35394 BentoML: malicious bento archive RCE via Jinja2 SSTI
CVE-2026-35044 BentoML: cmd injection RCE on cloud build infra
CVE-2026-35043 LiteLLM: auth bypass via JWT cache key collision
CVE-2026-35030 LiteLLM: auth bypass allows RCE and full takeover
CVE-2026-35029 vLLM: OOM DoS via unbounded video frame decoding
CVE-2026-34755 vLLM: SSRF in batch API exposes cloud metadata endpoints
CVE-2026-34753 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