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 512 results — has patchpraisonaiagents: SSRF leaks cloud IAM credentials
CVE-2026-34954 PraisonAI: sandbox escape via shell=True blocklist bypass
CVE-2026-34955 PraisonAI: 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: hardlink path traversal leaks sensitive files
CVE-2026-34446 ONNX: property overwrite via crafted model file
CVE-2026-34445 ONNX: symlink path traversal allows arbitrary file read
CVE-2026-27489 Anthropic SDK: TOCTOU symlink escape in async memory tool
CVE-2026-34452 anthropic-ai/sdk: memory tool path traversal escape
CVE-2026-34451 anthropic-sdk: insecure file perms expose agent memory
CVE-2026-34450 OpenClaw: .npmrc hijack enables RCE on plugin install
GHSA-m3mh-3mpg-37hw OpenClaw: HTTP scope bypass enables model enumeration
GHSA-68f8-9mhj-h2mp OpenClaw: sandbox escape via mediaUrl path traversal
GHSA-hr5v-j9h9-xjhg MLflow: RCE via unsanitized model dependency specs
CVE-2025-15379 MLflow: path traversal enables sandbox escape, file overwrite
CVE-2025-15036 openclaw: webhook rate-limit bypass enables token brute-force
CVE-2026-35646 openclaw: unauthenticated webhook parsing enables DoS
CVE-2026-35640 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