CVSS 3.1
Вероятност да бъде експлоатирана в следващите 30 дни (EPSS)
Атакува се
Време до експлоатация
Атакува се по мрежата, без особени условия, с обикновен потребителски вход и без действие от потребителя.
- Експлоатация: няма данни за експлоатация
- Атаката не може да се автоматизира
Описание
Оригинално описание
vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the /v1/completions/derender and /v1/chat/completions/derender endpoints accept caller-supplied GenerateResponse objects whose generate_responses, choices, token_ids, prompt_logprobs, logprobs.content, top_logprobs, and routed_experts structures are processed by OnlineDerenderer and tokenizer.decode before max_model_len, max_tokens, max_num_seqs, or response-size limits are enforced, allowing an authenticated API client to consume excessive CPU and memory and produce oversized responses. This issue is fixed in version 0.26.0.
Засегнати продукти
- vllm-project vllm: < 0.26.0
Вид слабост
История
- 17 август 2026 Публикувано
Други уязвимости в vllm-project vllm
Първоизточници
- https://www.cve.org/CVERecord?id=CVE-2026-71486
- https://nvd.nist.gov/vuln/detail/CVE-2026-71486
- https://github.com/vllm-project/vllm/security/advisories/GHSA-8737-qx52-hjff
- https://github.com/vllm-project/vllm/pull/47260
- https://github.com/vllm-project/vllm/commit/8e61b646e2d157f9b93451fa048f9c8530c8a67b
- https://github.com/vllm-project/vllm/releases/tag/v0.26.0