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 patchfickling: Protection Bypass circumvents security controls
GHSA-wccx-j62j-r448 fickling: security flaw enables exploitation
GHSA-mxhj-88fx-4pcv mlflow: Path Traversal enables file access
CVE-2026-2033 picklescan: Allowlist Bypass evades input filtering
GHSA-97f8-7cmv-76j2 pydantic-ai: SSRF allows internal network access
CVE-2026-25580 sagemaker: security flaw enables exploitation
CVE-2026-1777 picklescan: Deserialization enables RCE
GHSA-9m3x-qqw2-h32h lollms: Access Control bypass enables privilege escalation
CVE-2026-1117 mlflow: security flaw enables exploitation
CVE-2025-10279 chainlit: SSRF allows internal network access
CVE-2026-22219 keras: Resource Exhaustion enables DoS
CVE-2026-0897 mlflow: security flaw enables exploitation
CVE-2025-14279 fickling: Deserialization enables RCE
CVE-2026-22612 fickling: Allowlist Bypass evades input filtering
CVE-2026-22609 fickling: Allowlist Bypass evades input filtering
CVE-2026-22608 fickling: Allowlist Bypass evades input filtering
CVE-2026-22607 fickling: Allowlist Bypass evades input filtering
CVE-2026-22606 vllm: Input Validation flaw enables exploitation
GHSA-mcmc-2m55-j8jj picklescan: Path Traversal enables file access
GHSA-9726-w42j-3qjr picklescan: Code Injection enables RCE
GHSA-46h3-79wf-xr6c 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