TensorRT-LLM: Code exec via insecure deserialization on model load
CVSS 6.4CVE-2026-24220NVIDIA / GPU stackcurated
Impact
Code exec via insecure deserialization on model load
Who can reach it
Malicious model artifact
What to do
Bump TensorRT-LLM; rebuild serving images
References
Related entries
- TensorRT-LLM: Missing authentication in configuration processingCVE-2026-24259 · TensorRT-LLMMedium
- TensorRT-LLM: Code exec via insecure deserializationCVE-2026-24142 · TensorRT-LLMMedium
- TensorRT-LLM: Unsafe external file loadingCVE-2026-24226 · TensorRT-LLMMedium
- TensorRT-LLM: DoS via large tensor allocationCVE-2026-24271 · TensorRT-LLMMedium
- TensorRT-LLM: DoS / memory corruption (insufficient tensor validation)CVE-2026-47470 · TensorRT-LLMMedium
- TensorRT-LLM: DoS via assertion failureCVE-2026-47475 · TensorRT-LLMMedium
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.