CVE-2026-41523
vLLM is an inference and serving engine for large language models …
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.
What to do now
- Check your exposureFind out whether the affected software runs anywhere in your environment, including systems of suppliers.
- UpdateInstall the version in which the vendor fixed the vulnerability. The references lead to the advisory.
- Limit access until thenIf you cannot update at once, take the system off the internet or restrict who can reach it.
References
- github.com/vllm-project/vllm/security/advisories/GHSA-q8gq-377p-jq3r
- github.com/vllm-project/vllm/commit/b3c7ffcab82c2439726f8cb213800f6f38c023d3
- huntr.com/bounties/dcb05b04-e625-41e7-adbc-bbae0cc2d64c
- github.com/advisories/GHSA-q8gq-377p-jq3r
- access.redhat.com/security/cve/CVE-2026-41523
- bugzilla.redhat.com/show_bug.cgi?id=2491582
- security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-41523.json
- access.redhat.com/errata/RHSA-2026:36005
- nvd.nist.gov/vuln/detail/CVE-2026-41523
- cve.org/CVERecord?id=CVE-2026-41523
Data: CVE list and the NVD. This product uses data from the NVD API but is not endorsed or certified by the NVD.