CVE-2026-47155

The record

vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.22.0, vLLM's revision pinning controls do not consistently apply to all artifacts loaded for a model. A deployment that supplies --revision or --code-revision can still load dynamic code, GGUF files, image processors, retrieval side weights, or same-repository subfolder weights/config from an unpinned/default revision. This is a supply-chain integrity issue for pinned vLLM deployments. Operators can believe they are serving a reviewed model revision while vLLM resolves behavior-affecting nested or sibling artifacts outside that reviewed revision. This vulnerability is fixed in 0.22.0.

Affected packages

Related vulnerabilities

• CVE-2026-102682 Pipecat is an open-source Python framework for building real-time voice and multimodal… CWE-345
• CVE-2026-104850 MCP TypeScript SDK is the official TypeScript SDK for Model Context Protocol servers and… CWE-345
• CVE-2026-102275 PyJWT is a Python implementation of JSON Web Token standards. CWE-345
• CVE-2026-102267 PyJWT is a Python implementation of JSON Web Token standards. CWE-345
• CVE-2026-19941 An inapplicable NSEC record may be accepted by a `named` resolver as proof that no… CWE-345
• CVE-2026-77955 In NLnet Labs Unbound 1.13.2 up to and including 1.26.1, a vulnerability in ZONEMD… CWE-345
• CVE-2026-89251 AVideo through commit c3edcc274c389816d434acadac07ee78eaf330c1 fails to validate ad… CWE-345
• CVE-2026-86809 The Persian Elementor WordPress plugin from 2.7.10 before 2.8.2 does not verify that the… CWE-345