PYSEC-2026-2013
vLLM: Resource-Exhaustion (DoS) through Malicious Jinja Template in OpenAI-Compatible Server
Ciclo de vida de la vulnerabilidad
| Fecha | Fase | Evento | Detalle |
|---|---|---|---|
| Remediación | Parche 0.11.0 | vllm · -276 d desde divulgación | |
| Divulgación | Publicada | PYSEC-2026-2013 divulgada | |
| Divulgación | Modificada | Última actualización del registro | |
| Monitoreo | Detectada | Ingresó al índice |
Summary
A resource-exhaustion (denial-of-service) vulnerability exists in multiple endpoints of the OpenAI-Compatible Server due to the ability to specify Jinja templates via the `chat_template` and `chat_template_kwargs` parameters. If an attacker can supply these parameters to the API, they can cause a service outage by exhausting CPU and/or memory resources.
Details
When using an LLM as a chat model, the conversation history must be rendered into a text input for the model. In `hf/transformer`, this rendering is performed using a Jinja template. The OpenAI-Compatible Server launched by vllm serve exposes a `chat_template` parameter that lets users specify that template. In addition, the server accepts a `chat_template_kwargs` parameter to pass extra keyword arguments to the rendering function.
Because Jinja templates support programming-language-like constructs (loops, nested iterations, etc.), a crafted template can consume extremely large amounts of CPU and memory and thereby trigger a denial-of-service condition.
Importantly, simply forbidding the `chat_template` parameter does not fully mitigate the issue. The implementation constructs a dictionary of keyword arguments for `apply_hf_chat_template` and then updates that dictionary with the user-supplied `chat_template_kwargs` via `dict.update`. Since `dict.update` can overwrite existing keys, an attacker can place a `chat_template` key inside `chat_template_kwargs` to replace the template that will be used by `apply_hf_chat_template`.
# vllm/entrypoints/openai/serving_engine.py#L794-L816
_chat_template_kwargs: dict[str, Any] = dict(
chat_template=chat_template,
add_generation_prompt=add_generation_prompt,
continue_final_message=continue_final_message,
tools=tool_dicts,
documents=documents,
)
_chat_template_kwargs.update(chat_template_kwargs or {})
request_prompt: Union[str, list[int]]
if isinstance(tokenizer, MistralTokenizer):
...
else:
request_prompt = apply_hf_chat_template(
tokenizer=tokenizer,
conversation=conversation,
model_config=model_config,
**_chat_template_kwargs,
)Impact
If an OpenAI-Compatible Server exposes endpoints that accept `chat_template` or `chat_template_kwargs` from untrusted clients, an attacker can submit a malicious Jinja template (directly or by overriding `chat_template` inside `chat_template_kwargs`) that consumes excessive CPU and/or memory. This can result in a resource-exhaustion denial-of-service that renders the server unresponsive to legitimate requests.
Fixes
- https://github.com/vllm-project/vllm/pull/25794
Rangos afectados
Estado del parche por paquete
| Paquete / producto | Estado | Corregida en | Desde divulgación | Última versión |
|---|---|---|---|---|
pypivllm |
Corregida | 0.11.0 | -276 d | 0.33.0 no afectada |
0.11.0Arsenal público
Sin exploits, módulos ni PoC públicos conocidos a la fecha de verificación.
https://github.com/advisories/GHSA-6fvq-23cw-5628https://nvd.nist.gov/vuln/detail/CVE-2025-61620https://github.com/vllm-project/vllm/security/advisories/GHSA-6fvq-23cw-5628https://github.com/vllm-project/vllm/pull/25794https://github.com/vllm-project/vllm/commit/7977e5027c2250a4abc1f474c5619c40b4e5682fhttps://github.com/vllm-project/vllmhttps://pypi.org/project/vllmLas referencias externas se muestran para copiar: cve.llama.ec no lo redirige a otros sitios.
