All vulnerabilities

Servers and applications

CVE-2026-71486

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

Severity
Medium 4.3
Published
27 Jul 2026
Last changed
23 Oct 2026
Added to UpHeron
3 Nov 2026
Fixed in
0.26.0
Exploit chance
0.4% in the next 30 daysHigher than 32% of CVEs. EPSS by FIRST, 19 Nov 2026
Weakness
Uncontrolled resource consumption (CWE-400)Allocation without limits (CWE-770)
Attack
Over the network · Needs a user account · No user action needed
Attacker can
Slow it down
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L
Also known as
GHSA-8737-qx52-hjff
Sources
NVD, Project advisories (GitHub)

Description

The /v1/completions/derender and /v1/chat/completions/derender endpoints accept caller-supplied GenerateResponse objects and postprocess every nested choices[*].token_ids list directly. Unlike the normal render/generate path, derender does not enforce model context length, resolved max_tokens, max_num_seqs, choice-count, or response-size bounds before detokenizing and returning the supplied token IDs. An authenticated API client can therefore make the CPU-only render frontend, or any server exposing these /v1 derender routes, spend CPU and memory proportional to attacker-chosen generated-output-shaped JSON rather than to a bounded generation result.

The render router registers /v1/chat/completions/derender and /v1/completions/derender in vllm/entrypoints/serve/render/api_router.py, and the OpenAI API server attaches this router whenever "generate" or "render" is in supported_tasks (vllm/entrypoints/openai/api_server.py).

From vllm-project/vllm's security advisory. Shortened; the full text is there.

Affected software

SoftwareAffected versions
vLLMServers and applications · cpe:a:vllm:vllm
  • Every version before 0.26.0
vLLMServers and applications · github:vllm-project/vllm
  • Every version before 0.26.0

About vLLM

open-source software for large language model inference

From Wikidata, CC0 1.0.
Docker Hub pulls
44,195,225Docker Hub, 15 Nov 2026
GitHub stars
96,943GitHub, 15 Nov 2026
Forks
24,836GitHub, 15 Nov 2026
Latest release
v0.33.0rc3GitHub, 15 Nov 2026
Released
2 Nov 2026GitHub
License
Apache Software License 2.0Wikidata
First published on GitHub
9 Feb 2023GitHub

References

  • NVD https://nvd.nist.gov/vuln/detail/CVE-2026-71486
  • CVE.org https://www.cve.org/CVERecord?id=CVE-2026-71486
  • GitHub Advisory Database https://github.com/advisories/GHSA-8737-qx52-hjff
  • github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-8737-qx52-hjff