Vulnerability Description
vLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1 and prior to version 0.14.0, vLLM loads Hugging Face `auto_map` dynamic modules during model resolution without gating on `trust_remote_code`, allowing attacker-controlled Python code in a model repo/path to execute at server startup. An attacker who can influence the model repo/path (local directory or remote Hugging Face repo) can achieve arbitrary code execution on the vLLM host during model load. This happens before any request handling and does not require API access. Version 0.14.0 fixes the issue.
CVSS Score
HIGH
Affected Products
| Vendor | Product | Versions |
|---|---|---|
| Vllm | Vllm | >= 0.10.1, < 0.14.0 |
Related Weaknesses (CWE)
References
- https://github.com/vllm-project/vllm/commit/78d13ea9de4b1ce5e4d8a5af9738fea71fb0Patch
- https://github.com/vllm-project/vllm/pull/32194Issue TrackingPatch
- https://github.com/vllm-project/vllm/releases/tag/v0.14.0ProductRelease Notes
- https://github.com/vllm-project/vllm/security/advisories/GHSA-2pc9-4j83-qjmrPatchVendor Advisory
FAQ
What is CVE-2026-22807?
CVE-2026-22807 is a vulnerability with a CVSS score of 8.8 (HIGH). vLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1 and prior to version 0.14.0, vLLM loads Hugging Face `auto_map` dynamic modules during model resolu...
How severe is CVE-2026-22807?
CVE-2026-22807 has been rated HIGH with a CVSS base score of 8.8/10. Review the CVSS metrics above for detailed severity breakdown.
Is there a patch for CVE-2026-22807?
Check the references section above for vendor advisories and patch information. Affected products include: Vllm Vllm.