Database/AI/ML frameworks & serving
picklescan (model scanner): Scanner fails to detect malicious pickles when ZIP flag bits are flipped
CVSS 9.8CVE-2025-1945AI/ML frameworks & servingcurated
Impact
Scanner fails to detect malicious pickles when ZIP flag bits are flipped
Who can reach it
Customer-supplied PyTorch archive submitted to a provider's "we scan your models" control
What to do
Direct hit on the provider's own control plane. Upgrade picklescan and stop treating a clean scan as proof of safety
References
Related entries
- NVIDIA Triton: Stack buffer overflowCVE-2025-23310 · NVIDIA TritonCritical
- NVIDIA Triton: Stack overflow via crafted requestCVE-2025-23311 · NVIDIA TritonCritical
- NVIDIA Triton Inference Server (Python backend): Attacker-controlled input in the Python backendCVE-2025-23316 · NVIDIA Triton Inference Server (Python backend)Critical
- BentoML: RCE via insecure deserializationCVE-2025-27520 · BentoMLCritical
- BentoML: Insecure deserialization RCE prior to 1.4.8CVE-2025-32375 · BentoMLCritical
- PyTorch (`torch.load`): RCE via unsafe deserialization even with `weights_only=True`CVE-2025-32434 · PyTorch (`torch.load`)Critical
This entry is curated: imported from vendor advisories with machine assistance, not yet individually verified. Confirm against your vendor's advisory before acting, and report anything wrong.