GHSA-GX7P-2J49-HFQ4
vLLM : DoS via unvalidated mm_processor_kwargs in multimodal image processors (Isaac, InternVL, H2OVL, etc.)
Ciclo de vida de la vulnerabilidad
| Fecha | Fase | Evento | Detalle |
|---|---|---|---|
| Remediación | Parche 0.31.0 | vllm · -18 d desde divulgación | |
| Divulgación | Publicada | GHSA-GX7P-2J49-HFQ4 divulgada | |
| Divulgación | Modificada | Última actualización del registro | |
| Monitoreo | Detectada | Ingresó al índice |
Summary
API clients can supply arbitrary `mm_processor_kwargs` per request. vLLM
forwards these values through the multimodal rendering and processing pipeline
to Hugging Face and custom image/video processor constructors and calls.
Resource-sensitive values such as image size, patch size, patch count, crop
count, or frame count can therefore be controlled by a remote client.
For processors that upscale inputs, a single request can force an allocation
large enough to terminate the API server or worker with an out-of-memory
condition.
Affected Components
The per-request field was introduced in commit
`041e29471671a3d43afedb6a749421d56ef4d3e7` and first shipped in v0.7.3.
The generic forwarding path remains present in current `main`.
The Isaac path is a concrete high-amplification example:
- `ChatCompletionRequest.mm_processor_kwargs`
- `OnlineRenderer` request extras
- `MMProcessorInputs.hf_processor_mm_kwargs`
- `BaseMultiModalProcessor.info.get_hf_processor(**hf_processor_mm_kwargs)`
- `IsaacProcessingInfo.get_image_processor(**kwargs)`
- `IsaacImageProcessor(**kwargs)`
- `process_vision_for_patches()`
Equivalent constructor forwarding exists in InternVL-derived processors,
H2OVL, Step3VL, NemotronVL, and other multimodal processors. The issue is at
the shared remote-input boundary and is not limited to a fixed model list.
Impact
- Availability: one request can exhaust CPU or GPU memory and terminate a
- Scope: all users of the affected service instance lose availability.
- Authentication: vLLM's API key is optional, so deployments without an
Remediation
Reject non-empty per-request `mm_processor_kwargs` at every API-server request
schema by default. Operators serving only trusted clients can explicitly opt
in to the existing override behavior. Server-level `--mm-processor-kwargs` and
offline `LLM` overrides remain available.
This shared boundary covers current and future multimodal processors instead
of maintaining a model-specific list or a denylist that can miss custom
processor arguments.
A patch for this was merged here: https://github.com/vllm-project/vllm/pull/58830
Rangos afectados
Estado del parche por paquete
| Paquete / producto | Estado | Corregida en | Desde divulgación | Última versión |
|---|---|---|---|---|
pypivllm |
Corregida | 0.31.0 | -18 d | 0.34.0 no afectada |
0.31.0Arsenal público
Sin exploits, módulos ni PoC públicos conocidos a la fecha de verificación.
https://nvd.nist.gov/vuln/detail/CVE-2026-114055https://github.com/vllm-project/vllm/security/advisories/GHSA-gx7p-2j49-hfq4https://github.com/vllm-project/vllm/pull/58830https://github.com/vllm-project/vllm/commit/31f2e70cd3e403aaa471fb7fe3d33a7207aaf3cchttps://github.com/vllm-project/vllmhttps://github.com/vllm-project/vllm/releases/tag/v0.31.0https://www.vulncheck.com/advisories/vllm-0.7.3-before-0.31.0-dos-via-unvalidated-mm-processor-kwargsLas referencias externas se muestran para copiar: cve.llama.ec no lo redirige a otros sitios.
