{"id":"CVE-2026-100653","summary":"vLLM 0.22.1 before 0.28.0 Incomplete Artifact Pin Propagation","details":"vLLM is an inference and serving engine for large language models. In versions from 0.22.1 through 0.28.0, the operator-supplied model revision pin (--revision / --code-revision) is not propagated to several Hugging Face artifact loads for the FunAudioChat and Tarsier2 architectures: the WhisperFeatureExtractor and speech_tokenizer PreTrainedTokenizerFast loads in vllm/model_executor/models/funaudiochat.py and the Qwen2VLConfig.from_pretrained call used by Tarsier2ProcessingInfo in vllm/model_executor/models/qwen2_vl.py. As a result, deployments pinned to a reviewed revision still resolve these behavior-affecting processor, tokenizer, and config artifacts from the repository's default revision, so a later change to the upstream default branch can alter audio preprocessing, speech tokenizer behavior, or Tarsier2 configuration without any change to the operator's configured pin. This is a supply-chain integrity and reproducibility failure for pinned deployments; it is residual to the earlier fix tracked as GHSA-3ww4-5jv9-j5gm / CVE-2026-47155 and does not constitute remote code execution or a trust_remote_code=False bypass. The issue is fixed in version 0.28.0.","aliases":["GHSA-hhv2-872h-628q"],"modified":"2026-09-30T03:30:26.512657799Z","published":"2026-09-26T13:23:22.605Z","database_specific":{"cna_assigner":"VulnCheck","cwe_ids":["CWE-348"],"osv_generated_from":"https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/100xxx/CVE-2026-100653.json"},"references":[{"type":"ADVISORY","url":"https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/100xxx/CVE-2026-100653.json"},{"type":"ADVISORY","url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-hhv2-872h-628q"},{"type":"ADVISORY","url":"https://nvd.nist.gov/vuln/detail/CVE-2026-100653"},{"type":"ADVISORY","url":"https://www.vulncheck.com/advisories/vllm-0.22.1-before-0.28.0-incomplete-artifact-pin-propagation"},{"type":"FIX","url":"https://github.com/vllm-project/vllm/commit/d26a28ab033697f55a1414b5b0435de7cd6045b6"}],"affected":[{"ranges":[{"type":"GIT","repo":"https://github.com/vllm-project/vllm","events":[{"introduced":"0decac0d96c42b49572498019f0a0e3600f50398"},{"fixed":"2cf0a6915ce544dc493a0990f2ea38d81601128a"},{"fixed":"d26a28ab033697f55a1414b5b0435de7cd6045b6"}],"database_specific":{"extracted_events":[{"introduced":"0.22.1"},{"fixed":"0.28.0"}],"source":["DESCRIPTION","REFERENCES"]}}],"database_specific":{"source":"https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2026-100653.json"}}],"schema_version":"1.9.0","severity":[{"type":"CVSS_V4","score":"CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:L/VI:H/VA:N/SC:N/SI:N/SA:N"}]}