Attestkeep
Language: English
Sign up

Vulnerabilities / CVE-2026-22807

critical

CVE-2026-22807

vLLM: vLLM: Arbitrary code execution via untrusted model loading

Published Modified CWE 94
In the Trivy database since at least 24 Oct 2026, 07:11 UTCWhen it arrived before that build is not recorded.

Severity by source

NVD9.8CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
GHSA8.8CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Red Hat8.8CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

Trivy's own label is CRITICAL. Rated critical by NVD. Rated lower by GHSA (high), Red Hat (high).

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.

Affected packages and fixed versions

SourcePackageFixed in
chainguardpy3-vllm-cuda-12.4, tritonserver-backend-vllm-cuda-12.9, tritonserver-backend-vllm-cuda-13.00.14.0-r0 and 2 more
pip::GitHub Security Advisory pipvllm0.14.0
Show all 4 entries from 2 sources
SourcePackageFixed in
chainguardpy3-vllm-cuda-12.40.14.0-r0
chainguardtritonserver-backend-vllm-cuda-12.925.9.0_git20260318-r0
chainguardtritonserver-backend-vllm-cuda-13.025.11-r2
pip::GitHub Security Advisory pipvllm0.14.0

References

All 23 references

Vulnerability data compiled from the Trivy vulnerability database (trivy-db, Aqua Security, Apache License 2.0), which aggregates third-party advisories. CVE records are published by The MITRE Corporation under the CVE Terms of Use; CVE is a trademark of MITRE. This product uses data from the NVD API but is not endorsed or certified by the NVD. Severity, titles and advisory data from the GitHub Advisory Database (CC BY 4.0), Red Hat security data (CC BY 4.0) and the other sources linked on each entry. Entries may be summarised or re-formatted; the linked original is the authoritative record.