High [CVE-2026-41523] Arbitrary code execution via malicious HuggingFace model
This high-severity Red Hat Linux advisory covers CVE-2026-41523.
Android app · Google Play
Monitor future Red Hat Linux CVEs from your phone.
Choose a whole vendor or a precise platform, then receive matching security advisories by phone notification, email, or both. Coverage follows 32 official vendor sources and 160+ reviewed platform categories.
Summary
Arbitrary code execution via malicious HuggingFace model. Red Hat rates this important (CVSS 7.5).
Weakness: CWE-617. Red Hat lists fixing advisory RHSA-2026:36006 with package rhaiis/vllm-cuda-rhel9:1782951012, rhaiis/vllm-rocm-rhel9:1782951244.
Affected versions
No affected-version range was extracted from the source record. The vendor advisory is authoritative — check it before change work.
Official advisory · high-confidence parse· fetched 2 months ago·verify at source
- rhaiis/vllm-cuda-rhel9:1782951012
- rhaiis/vllm-rocm-rhel9:1782951244
- RHSA-2026:36006
Official advisory · high-confidence parse· fetched 2 months ago·verify at source
Mitigation checklist
- Avoid running vLLM with python -O or PYTHONOPTIMIZE=1 until updated packages are available. Only load models from trusted sources. Restrict who can deploy or update models on inference endpoints. Apply network access controls and authentication in front of vLLM APIs.
Official advisory · high-confidence parse· fetched 2 months ago·verify at source
Discussion(0)
No comments yet. Share field notes, upgrade gotchas, or questions — verify against the vendor advisory before acting on community advice.
Sign in to join the discussion.