CSIRTS // UNIFIED SECURITY ADVISORY FEEDSYS ● ONLINE · POWERED BY INTELFUSIONS.COM

GHSA-3ww4-5jv9-j5gm: vLLM's Artifact Pin Decay allows pinned deployments to load unpinned code, weights, and processors

mediumCVSS 6.5CVE-2026-47155
Summary 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. Details The expected invariant is: When a vLLM operator supplies a model or code revision pin, every code, config, processor, weight file, side weight, and same-repository subfolder artifact loaded as part of that model should resolve under that pin unless vLLM exposes and enforces a separate explicit pin for that artifact. Current main was verified affected at commit 3795d7acf431980e62e738493f437ae2a51549da. Affected source boundaries: - vllm/model_executor/models/registry.py:1045-1051 and :1058-1064 - _try_resolve_transformers() passes revision=model_config.revision and trust_remote_code=model_config.trust_remote_code, but omits code_revision=model_config.code_revision for external auto_map dynamic module imports. - vllm/model_executor/model_loader/gguf_loader.py:58-60 - The direct-file GGUF form repo/file.gguf calls hf_hub_download(repo_id=repo_id, filename=filename) without passing revision. - vllm/model_executor/models/roberta.py:203-209 - BGE-M3 secondary sparse and ColBERT side weights are declared with revision=None. - vllm/model_executor/models/kimi_k25.py:111-114 - Kimi-K2.5 calls cached_get_image_processor() without passing model_config.revision. - vllm/model_executor/models/kimi_audio.py:92-95 - Kimi-Audio loads Whisper config from the whisper-large-v3 subfolder without a revision argument. - vllm/model_executor/models/kimi_audio.py:425-430 - Kimi-Audio declares same-repository whisper-large-v3 seconda

Details

Source
GitHub Security Advisories (INTL · database · site)
Severity
medium — CVSS 6.5
Published
2026-06-10
Last updated
2026-07-17
Exploitation
Not in CISA KEV at last sync

Original advisory: https://github.com/advisories/GHSA-3ww4-5jv9-j5gm

Exploitation outlook

EPSS (FIRST.org) estimates each CVE’s probability of exploitation in the next 30 days — here is the CSIRTS.com read on those numbers.

Referenced CVEs

CVECSIRTS overviewExternal
CVE-2026-47155coverage & exploitation statusNVD · CVE.org

More from GitHub Security Advisories