CVE-2026-41523
7.5
CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H
Summary
vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.22.0, an assert-based security check in vLLM's activation function loading allows any unauthenticated attacker to achieve arbitrary code execution on the server by publishing a malicious HuggingFace model, when vLLM runs in Python optimized mode (python -O or PYTHONOPTIMIZE=1). This vulnerability is fixed in 0.22.0.
Affected Software
| Vendor | Product | Version Range | Status |
|---|---|---|---|
| vllm-project | vllm | < 0.22.0 | affected |
Weaknesses
- CWE-94: CWE-94: Improper Control of Generation of Code ('Code Injection')
- CWE-617: CWE-617: Reachable Assertion
ADP Enrichment
CISA ADP Vulnrichment
- SSVC:
- Exploitation: none
- Automatable: no
- Technical Impact: total
vllm: vLLM: Arbitrary code execution via malicious HuggingFace model
Additional References
- https://access.redhat.com/security/cve/CVE-2026-41523
- https://bugzilla.redhat.com/show_bug.cgi?id=2491582
- https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-41523.json
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-q8gq-377p-jq3r
- https://github.com/vllm-project/vllm/commit/b3c7ffcab82c2439726f8cb213800f6f38c023d3
- https://huntr.com/bounties/dcb05b04-e625-41e7-adbc-bbae0cc2d64c
Feedback
Was this page helpful?
Glad to hear it! Please tell us how we can improve.
Sorry to hear that. Please tell us how we can improve.