PYSEC-2026-4324 CVE-2026-100653 GHSA-hhv2-872h-628q

vLLM is an inference and serving engine for large language models.

Medium PyPI

Severity: 0.0 / 10; Medium · CVSS 4.0
Exploit chance (EPSS): 0.34%; Chance of exploitation in the next 30 days. Higher than 27.46% of scored vulnerabilities.
Known exploited: No; Not in CISA's catalog
Weakness: CWE-348 Use of Less Trusted Source
Fix: 0.28.0; Upgrade vllm to this version or later

Description

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.

Affected versions

PyPI

Package	Vulnerable	Fixed in
vllm	`>= 0.22.1, < 0.28.0`	`0.28.0`

How to fix

Move to the fixed version or later with your package manager, update the lockfile, and run your tests. If the package only arrives through another dependency, upgrade that dependency first. If none of its releases pulls a fixed version yet, force the version with your package manager's override.

vllm PyPI → `0.28.0`

pip

pip install --upgrade "vllm>=0.28.0"

poetry

poetry add "vllm>=0.28.0"

uv

uv add "vllm>=0.28.0"

Severity breakdown

CVSS 4.0 0.0

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/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X

Attack vector: Network
Attack complexity: High
Attack requirements: Present
Privileges required: None
User interaction: None
Confidentiality (vulnerable system): Low
Integrity (vulnerable system): High
Availability (vulnerable system): None
Confidentiality (subsequent systems): None
Integrity (subsequent systems): None
Availability (subsequent systems): None
Exploit maturity: Not defined
Scope: X

CVSS 3.1 6.5

CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:L/I:H/A:N

Attack vector: Network
Attack complexity: High
Privileges required: None
User interaction: None
Scope: Unchanged
Confidentiality: Low
Integrity: High
Availability: None

Weakness

CWE-348: Use of Less Trusted Source

The product has two different sources of the same data or information, but it uses the source that has less support for verification, is less trusted, or is less resistant to attack.

References

Timeline

Sep 26, 2026 Published
Oct 23, 2026 Last updated by the source
Oct 31, 2026 Latest EPSS score

Advisory	Severity	Why it's related
GHSA-8397-8qf6-f2gm vLLM: Phi-4 multimodal audio encoder materializes and retains full attention matrices: a single max-length audio OOM-crashes the vLLM engine	Medium	Also affects vllm
GHSA-x567-49g5-p4cf vLLM: Responses API bypasses trust_request_chat_template for chat_template_kwargs	Medium	Also affects vllm
GHSA-vvpg-rrww-wpmh vLLM: Permissive default CORS origins allow cross-origin requests to the vLLM HTTP server	Medium	Also affects vllm
GHSA-q97c-p368-75c4 vLLM: Out-of-vocabulary prompt token id passes input validation and triggers a CUDA device-side assert (engine crash / DoS)	Medium	Also affects vllm
GHSA-h3rc-j82p-2c3h vLLM: Untrusted EPS inputs can trigger denial of service or Ghostscript RCE	High	Also affects vllm
GHSA-gq5q-89c7-vhvx vLLM DeepSeek-OCR image processing vulnerable to denial of service	Medium	Also affects vllm
GHSA-6757-hggm-hp2w vLLM: Public multimodal SHM handle forgery reaches worker-side `pickle.loads()` with insecure serialization disabled	High	Also affects vllm
GHSA-542m-9234-8gvf vLLM: DoS via unbounded chat_template Jinja2 rendering exhausts the renderer thread pool	Medium	Also affects vllm

Is this in your code?

MergeHarbor checks every repository's dependencies against this database, ranks what matters by exploitability and reachability, routes it to the owning team and opens the fix pull request.

Check your repos with MergeHarbor