All vulnerabilities

Servers and applications

GHSA-hhv2-872h-628q

Incomplete artifact pin propagation in FunAudioChat and Tarsier2

Severity
Medium 6.5
Published
12 Sept 2026
Last changed
12 Sept 2026
Added to UpHeron
3 Nov 2026
Fixed in
0.28.0
Weakness
CWE-348
Attack
Over the network · Only under certain conditions · No login needed · No user action needed
Attacker can
Read some data · Change data
CVSS vector
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:L/I:H/A:N
Sources
Project advisories (GitHub)

Description

The fix for GHSA-3ww4-5jv9-j5gm / CVE-2026-47155 propagated --revision and --code-revision through several artifact boundaries, but supported FunAudioChat and Tarsier2 paths still omit the operator-supplied revision pin.

Remaining affected call sites:

  • vllm/model_executor/models/funaudiochat.py:556
  • vllm/model_executor/models/funaudiochat.py:560-562
  • vllm/model_executor/models/qwen2_vl.py:1796-1797

These loads can resolve FunAudioChat processor/tokenizer artifacts and Tarsier2 config outside the audited model revision selected by the operator.

Operators who pin FunAudioChat or Tarsier2 deployments to a reviewed Hugging Face revision can still load behavior-affecting processor/tokenizer/config artifacts from the repository default revision. A later default-branch change can alter audio preprocessing, speech tokenizer behavior, or Tarsier2 config without changing the operator's configured revision.

From vllm-project/vllm's security advisory. Shortened; the full text is there.

Affected software

SoftwareAffected versions
vLLMServers and applications · github:vllm-project/vllm
  • From 0.22.1 before 0.28.0

About vLLM

open-source software for large language model inference

From Wikidata, CC0 1.0.
Docker Hub pulls
44,195,225Docker Hub, 15 Nov 2026
GitHub stars
96,943GitHub, 15 Nov 2026
Forks
24,836GitHub, 15 Nov 2026
Latest release
v0.33.0rc3GitHub, 15 Nov 2026
Released
2 Nov 2026GitHub
License
Apache Software License 2.0Wikidata
First published on GitHub
9 Feb 2023GitHub

References