CVE-2026-71486
vLLM: Derender endpoints decode caller-supplied GenerateResponse token IDs without output bounds
Description
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.
INFO
Published Date :
Aug. 17, 2026, 8:16 p.m.
Last Modified :
Oct. 23, 2026, 4:10 p.m.
Remotely Exploit :
Yes !
Source :
[email protected]
CVSS Scores
| Score | Version | Severity | Vector | Exploitability Score | Impact Score | Source |
|---|---|---|---|---|---|---|
| CVSS | 134c704f-9b21-4f2e-91b3-4a467353bcc0 | |||||
| CVSS 3.1 | MEDIUM | [email protected] | ||||
| CVSS 3.1 | MEDIUM | MITRE-CVE |
Solution
- Update vLLM to version 0.26.0 or later.
- Apply security patches if available.
- Monitor system resource usage.
References to Advisories, Solutions, and Tools
Here, you will find a curated list of external links that provide in-depth
information, practical solutions, and valuable tools related to
CVE-2026-71486.
| URL | Resource |
|---|---|
| https://github.com/vllm-project/vllm/commit/8e61b646e2d157f9b93451fa048f9c8530c8a67b | Patch |
| https://github.com/vllm-project/vllm/pull/47260 | Issue Tracking Patch |
| https://github.com/vllm-project/vllm/releases/tag/v0.26.0 | Release Notes |
| https://github.com/vllm-project/vllm/security/advisories/GHSA-8737-qx52-hjff | Exploit Vendor Advisory Mitigation |
CWE - Common Weakness Enumeration
While CVE identifies
specific instances of vulnerabilities, CWE categorizes the common flaws or
weaknesses that can lead to vulnerabilities. CVE-2026-71486 is
associated with the following CWEs:
Common Attack Pattern Enumeration and Classification (CAPEC)
Common Attack Pattern Enumeration and Classification
(CAPEC)
stores attack patterns, which are descriptions of the common attributes and
approaches employed by adversaries to exploit the CVE-2026-71486
weaknesses.
We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).
Results are limited to the first 15 repositories due to potential performance issues.
The following list is the news that have been mention
CVE-2026-71486 vulnerability anywhere in the article.
The following table lists the changes that have been made to the
CVE-2026-71486 vulnerability over time.
Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.
-
CVE Translated by [email protected]
Oct. 23, 2026
Action Type Old Value New Value Added Translation Title: vllm de vllm-project, Description: vLLM es un motor de inferencia y servicio para grandes modelos de lenguaje. Antes de la versión 0.26.0, los puntos finales /v1/completions/derender y /v1/chat/completions/derender aceptan objetos GenerateResponse proporcionados por el llamador cuyas estructuras generate_responses, choices, token_ids, prompt_logprobs, logprobs.content, top_logprobs y routed_experts son procesadas por OnlineDerenderer y tokenizer.decode antes de que se apliquen los límites de max_model_len, max_tokens, max_num_seqs o tamaño de respuesta, permitiendo a un cliente API autenticado consumir CPU y memoria excesivas y producir respuestas sobredimensionadas. Este problema se corrige en la versión 0.26.0. -
Initial Analysis by [email protected]
Oct. 02, 2026
Action Type Old Value New Value Added CPE Configuration OR *cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:* versions up to (excluding) 0.26.0 Added Reference Type GitHub, Inc.: https://github.com/vllm-project/vllm/commit/8e61b646e2d157f9b93451fa048f9c8530c8a67b Types: Patch Added Reference Type GitHub, Inc.: https://github.com/vllm-project/vllm/pull/47260 Types: Issue Tracking, Patch Added Reference Type GitHub, Inc.: https://github.com/vllm-project/vllm/releases/tag/v0.26.0 Types: Release Notes Added Reference Type GitHub, Inc.: https://github.com/vllm-project/vllm/security/advisories/GHSA-8737-qx52-hjff Types: Exploit, Mitigation, Vendor Advisory -
CVE Modified by 134c704f-9b21-4f2e-91b3-4a467353bcc0
Aug. 18, 2026
Action Type Old Value New Value Added SSVC {'id': 'CVE-2026-71486', 'role': 'CISA Coordinator', 'options': [{'exploitation': 'none'}, {'automatable': 'no'}, {'technicalImpact': 'partial'}], 'version': '2.0.3', 'timestamp': '2026-08-18T12:34:35.419144Z'} -
New CVE Received by [email protected]
Aug. 17, 2026
Action Type Old Value New Value Added Affected [{'vendor': 'vllm-project', 'product': 'vllm', 'versions': [{'status': 'affected', 'version': '< 0.26.0'}]}] Added Description 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. Added CVSS V3.1 AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L Added CWE CWE-400 Added CWE CWE-770 Added Reference https://github.com/vllm-project/vllm/commit/8e61b646e2d157f9b93451fa048f9c8530c8a67b Added Reference https://github.com/vllm-project/vllm/pull/47260 Added Reference https://github.com/vllm-project/vllm/releases/tag/v0.26.0 Added Reference https://github.com/vllm-project/vllm/security/advisories/GHSA-8737-qx52-hjff