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 patchpicklescan: PyTorch gadget bypasses pickle RCE detection
GHSA-vr7h-p6mm-wpmh picklescan: detection bypass via PyTorch proxy RCE
GHSA-h3qp-7fh3-f8h4 picklescan: RCE bypass via torch.utils.collect_env
GHSA-f745-w6jp-hpxx picklescan: scanner bypass enables RCE via PyTorch function
GHSA-f4x7-rfwp-v3xw picklescan: detection bypass enables PyTorch model RCE
GHSA-86cj-95qr-2p4f picklescan: PyTorch bypass allows undetected RCE
GHSA-4r9r-ch6f-vxmx vLLM: RCE via eval() in Qwen3 Coder tool parser
CVE-2025-9141 picklescan: detection bypass allows malicious pickle exec
GHSA-9gvj-pp9x-gcfr skops: joblib fallback enables RCE via model load
CVE-2025-54886 ExecuTorch: heap buffer overflow RCE via model loading
CVE-2025-54949 ExecuTorch: integer overflow RCE on model load
CVE-2025-30404 ExecuTorch: heap buffer overflow RCE in model loading
CVE-2025-54951 ExecuTorch: integer overflow in model load → RCE
CVE-2025-30405 ExecuTorch: OOB read in model loader enables RCE
CVE-2025-54950 skops: RCE via MethodNode unsafe deserialization
CVE-2025-54413 skops: OperatorFuncNode type confusion → RCE
CVE-2025-54412 ExecuTorch: heap overflow in method load, RCE risk
CVE-2025-30402 llama-index: DocugamiReader MD5 hash collision drops chunks
CVE-2025-6211 llama_index: path traversal allows arbitrary file read
CVE-2025-6209 llama-index: JSONReader DoS via recursive JSON parsing
CVE-2025-5472 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