4.3

CVE-2026-71486

Exploit

vLLM: Derender endpoints decode caller-supplied GenerateResponse token IDs without output bounds

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.
Daten sind bereitgestellt durch National Vulnerability Database (NVD)
Vllm ≫ Vllm Version < 0.26.0
VulnDex Vulnerability Enrichment
Diese Information steht angemeldeten Benutzern zur Verfügung. Login Login
Zu dieser CVE wurde keine Warnung gefunden.
EPSS Metriken
Typ Quelle Score Percentile
EPSS FIRST.org 0.34% 0.272
CVSS Metriken
Quelle Base Score Exploit Score Impact Score Vector String
security-advisories@github.com 4.3 2.8 1.4
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L
CWE-400 Uncontrolled Resource Consumption

The product does not properly control the allocation and maintenance of a limited resource.

CWE-770 Allocation of Resources Without Limits or Throttling

The product allocates a reusable resource or group of resources on behalf of an actor without imposing any intended restrictions on the size or number of resources that can be allocated.

https://github.com/vllm-project/vllm/releases/tag/v0.26.0
Release Notes
https://github.com/vllm-project/vllm/commit/8e61b646e2d157f9b93451fa048f9c8530c8a67b
Patch
https://github.com/vllm-project/vllm/pull/47260
Patch
Issue Tracking
https://github.com/vllm-project/vllm/security/advisories/GHSA-8737-qx52-hjff
Vendor Advisory
Exploit
Mitigation