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 1616 resultsTensorFlow: security flaw enables exploitation
CVE-2026-2492 mlflow: Path Traversal enables file access
CVE-2026-2033 google-cloud-aiplatform: XSS enables session hijacking
CVE-2026-2472 ray: Missing Auth allows unauthenticated access
CVE-2026-27482 fickling: Allowlist Bypass evades input filtering
GHSA-83pf-v6qq-pwmr OpenClaw: prompt injection via unsanitized workspace path
CVE-2026-27001 OpenClaw: path traversal allows arbitrary file write
CVE-2026-26972 OpenClaw: path traversal enables local file exfiltration
CVE-2026-26321 OpenClaw: UI deception enables arbitrary command execution
CVE-2026-26320 sillytavern: SSRF allows internal network access
CVE-2026-26286 semantic-kernel: Code Injection enables RCE
CVE-2026-26030 OpenClaw: indirect prompt injection via Slack metadata
CVE-2026-24764 ffmpeg: security flaw enables exploitation
CVE-2025-12343 picklescan: Allowlist Bypass evades input filtering
GHSA-97f8-7cmv-76j2 smolagents: SSRF allows internal network access
CVE-2026-2654 keras: File Control enables path manipulation
CVE-2026-1669 langchain_community: SSRF allows internal network access
CVE-2026-26019 langchain-core: SSRF allows internal network access
CVE-2026-26013 n8n: Input Validation flaw enables exploitation
CVE-2026-25631 semantic-kernel: Path Traversal enables file access
CVE-2026-25592 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