vllm · Vulnerability
Historical advisory recorded 23 Oct 2026 15:48:27 UTC. Read the latest advisory.
cve-program · CVE-2026-41523
PublishedvLLM 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.
Read the publisher's advisoryAffected versions, risk and source history
cve-program · CVE-2026-41523
PublishedvLLM: Security Check Bypass via assert Statement in Activation Function Loading Allows Arbitrary Code Execution
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.
- Source published
- 22 Jun 2026 22:18:14 UTC
- Source modified
- 4 Sep 2026 12:04:58 UTC
- Saved here
- 23 Oct 2026 15:48:27 UTC
- Source terms
- CVE Program Terms of Use
Original source record · Cite this exact observation · Complete original publisher JSON
Source: cve-program · CVE Program Terms of Use. The publisher's wording is preserved. ChangeIntel groups the information and labels changes. The JSON record includes additional source fields.
CVSS 3.1 · 7.5 CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H