llamaCVEVulnerability Intelligence
/
Advisory · GitHub · PyPI · vllm

GHSA-H3RC-6MM3-GC2M

vLLM: Request-controlled mm_processor_kwargs.code_revision allows remote code execution

Parche disponible
Descargar PNG JSON
CVSS
—
high
Fuente: —
ExplotaciónSin evidenciaNo figura en CISA KEV
Exploits públicos0Ninguno conocido
Parche1 versiónPrimer parche a -22 d de la divulgación
Exposición24 dDesde la divulgación, 27 oct 2026, 10:36 a. m.
Detección20 dDesde la divulgación hasta su ingreso al índice
Timeline

Ciclo de vida de la vulnerabilidad

Hoy
Divulgación
Publicada +1
Explotación
Remediación
Parche 0.31.0
Monitoreo
Detectada
5 oct 26
27 oct 26
17 nov 26
20 nov 26
5 oct 26
17 oct 26
28 oct 26
9 nov 26
20 nov 26
FechaFaseEventoDetalle
Remediación Parche 0.31.0 vllm · -22 d desde divulgación
Divulgación Publicada GHSA-H3RC-6MM3-GC2M divulgada
Divulgación Modificada Última actualización del registro
Monitoreo Detectada Ingresó al índice
Resumen
Descripción del advisory
Texto original · GitHub · en inglés

Summary

An untrusted multimodal request can set `mm_processor_kwargs.code_revision`. When vLLM serves a model whose Hugging Face processor uses dynamic `auto_map` code and the operator enabled `--trust-remote-code`, this request value reaches `AutoProcessor.from_pretrained` and selects the Python revision imported by Transformers.

This lets a client replace the operator-reviewed processor module with code from another revision of the same model repository. The operator-selected model/data `revision` remains pinned; only the executed processor code changes.

Importing a Python module is arbitrary code execution in the vLLM API/renderer process. The PoC below demonstrates this with an import-time filesystem write. It is fully offline and does not require a GPU, model weights, or changes to a real Hub repository.

Affected snapshot

  • Repository: `vllm-project/vllm` https://github.com/vllm-project/vllm
  • Verified commit: `570735520942b6428ae98f1eb442c6d88adae55e` https://github.com/vllm-project/vllm/commit/570735520942b6428ae98f1eb442c6d88adae55e
  • Verified with Transformers 5.15.0 and 5.16.1
  • Affected release range has not been bisected

Affected configuration

The vulnerable path exists when all of the following are true:

  1. The served model's processor uses dynamic `auto_map.AutoProcessor` code.
  2. The operator enabled `trust_remote_code`.
  3. The server can fetch the request-selected revision, or it is already cached.
  4. The attacker can create or otherwise control a revision in the served model repository. An example is a Hugging Face community pull-request ref https://huggingface.co/docs/hub/en/repositories-pull-requests-discussions#where-in-the-git-repo-are-changes-stored when that repository permits them.
  5. A multimodal request reaches the processor path.

The default `trust_remote_code=False` configuration is not affected.

Attack surface

`mm_processor_kwargs` is accepted directly by public request models:

  • `TokenizeChatRequest.mm_processor_kwargs` https://github.com/vllm-project/vllm/blob/570735520942b6428ae98f1eb442c6d88adae55e/vllm/entrypoints/serve/tokenize/protocol.py#L111-L114
  • `ChatCompletionRequest.mm_processor_kwargs` https://github.com/vllm-project/vllm/blob/570735520942b6428ae98f1eb442c6d88adae55e/vllm/entrypoints/openai/chat_completion/protocol.py#L372-L375

`/tokenize` is particularly relevant because vLLM's authentication middleware guards only `/v1`, `/v2`, `/inference`, and `/cohere` prefixes:

  • `AuthenticationMiddleware` https://github.com/vllm-project/vllm/blob/570735520942b6428ae98f1eb442c6d88adae55e/vllm/entrypoints/serve/middleware/authenticate.py#L11-L62

Consequently, `/tokenize` remains unauthenticated even when `--api-key` is configured, unless an external proxy protects it. The vLLM Security Guide https://docs.vllm.ai/en/latest/usage/security/#unprotected-endpoints-no-api-key-required documents `/tokenize` as an unprotected endpoint.

Root cause

The request value follows this path:

  1. `OnlineRenderer.preprocess_chat` https://github.com/vllm-project/vllm/blob/570735520942b6428ae98f1eb442c6d88adae55e/vllm/renderers/online_renderer.py#L406-L435 places request `mm_processor_kwargs` in prompt extras.
  2. Multimodal rendering forwards those kwargs into processor construction through `MMProcessorInputs` https://github.com/vllm-project/vllm/blob/570735520942b6428ae98f1eb442c6d88adae55e/vllm/renderers/base.py#L751-L760 and `_process_multimodal_async` https://github.com/vllm-project/vllm/blob/570735520942b6428ae98f1eb442c6d88adae55e/vllm/renderers/base.py#L831-L847.
  3. `MultiModalConfig.merge_mm_processor_kwargs` https://github.com/vllm-project/vllm/blob/570735520942b6428ae98f1eb442c6d88adae55e/vllm/config/multimodal.py#L506-L518 overlays inference values on startup values, so the request wins.
  4. `cached_get_processor_without_dynamic_kwargs` https://github.com/vllm-project/vllm/blob/570735520942b6428ae98f1eb442c6d88adae55e/vllm/transformers_utils/processor.py#L344-L375 filters only recognized processor-call keys. `code_revision` is retained as a processor-construction kwarg.
  5. `cached_processor_from_config` https://github.com/vllm-project/vllm/blob/570735520942b6428ae98f1eb442c6d88adae55e/vllm/transformers_utils/processor.py#L380-L390 pins `revision` and `trust_remote_code`, but forwards the remaining kwargs without reserving `code_revision`.
  6. `get_processor` https://github.com/vllm-project/vllm/blob/570735520942b6428ae98f1eb442c6d88adae55e/vllm/transformers_utils/processor.py#L205-L245 calls `AutoProcessor.from_pretrained(..., revision=revision, trust_remote_code=trust_remote_code, **kwargs)`.
  7. Transformers `AutoProcessor.from_pretrained` https://github.com/huggingface/transformers/blob/v5.15.0/src/transformers/models/auto/processing_auto.py#L294-L302 uses `code_revision` to retrieve and import the dynamic module through `get_class_from_dynamic_module` https://github.com/huggingface/transformers/blob/v5.15.0/src/transformers/dynamic_module_utils.py#L474-L575, then removes it before loading processor data. This is why code comes from the attacker revision while configuration/data remain operator-pinned.

Request-time processor arguments are not separated from processor-construction arguments, and `code_revision` is not reserved.

Suggested remediation

  1. Separate processor-construction arguments from untrusted processor-call arguments. An allowlist of supported request-time preprocessing controls is safest.
  2. Reject `code_revision` and other loader/source controls in request `mm_processor_kwargs`, and pass `model_config.code_revision` explicitly as the only permitted processor-code revision.
  3. Add a regression test proving a request cannot change the loaded module revision while operator pins remain effective.
  4. Protect `/tokenize` with the configured authentication policy as defense in depth.

Expected safe behavior is either a 4xx response for reserved request keys or silently ignoring them before processor construction. Rejection is preferable because it makes attempted misuse visible.

A patch for this was merged here: https://github.com/vllm-project/vllm/pull/58830

Incluye detalles técnicos publicados por el investigador. Úselos solo para validar y corregir sus propios sistemas.

Versiones

Rangos afectados

Afectada Corregida Última
vllm≥ 0.7.3 < 0.31.0
0.7.3
0.31.0
0.34.0
Remediación

Estado del parche por paquete

Paquete / productoEstadoCorregida enDesde divulgaciónÚltima versión
pypivllm
Corregida 0.31.0 -22 d 0.34.0 no afectada
Versiones corregidas0.31.0
Explotación

Arsenal público

Sin exploits, módulos ni PoC públicos conocidos a la fecha de verificación.

Referencias
Advisoryhttps://nvd.nist.gov/vuln/detail/cve-2026-114053
Otrahttps://github.com/vllm-project/vllm/security/advisories/GHSA-h3rc-6mm3-gc2m
Otrahttps://github.com/vllm-project/vllm/pull/58830
Otrahttps://github.com/vllm-project/vllm/commit/31f2e70cd3e403aaa471fb7fe3d33a7207aaf3cc
Otrahttps://github.com/vllm-project/vllm
Otrahttps://github.com/vllm-project/vllm/releases/tag/v0.31.0
Otrahttps://www.vulncheck.com/advisories/vllm-0.7.3-before-0.31.0-rce-via-mm-processor-kwargs-code-revision

Las referencias externas se muestran para copiar: cve.llama.ec no lo redirige a otros sitios.