CVE-2026-71486mediumCWE-400CWE-770

CVE-2026-71486: medium-severity vulnerability in vllm-project vllm

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

Published · Updated

Follow this CVE+ Monitor vllm+ Monitor vllm

E-mail alert when it lands in KEV, gets a public PoC or its score goes up.

13Vexday Risk Score

No sign of exploitation. No public exploitation artifact known so far.

ssvc Trackcvss 4.3epss 0.4%
from disclosure to weapon49 days
Published on NVDAug 17
1st PoC+49d
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.
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L
Affected products
vllm-project · vllm
⚠ Public resources, to assess the exposure of systems you control or are authorized to test. Test only with authorization.
Related CVEs — vllm-project vllm

In the same product, most dangerous first.

CVE-2026-22778CRITICALvLLM leaks a heap address when PIL throws an errorEPSS 18.3%CVE-2025-32444CRITICALvLLM Vulnerable to Remote Code Execution via Mooncake IntegrationEPSS 1.8%CVE-2026-27893HIGHvLLM's hardcoded trust_remote_code=True in NemotronVL and KimiK25 bypasses user security opt-outEPSS 1.4%CVE-2026-48746CRITICALvLLM: OpenAI auth bypassEPSS 1.2%CVE-2026-22807HIGHvLLM affected by RCE via auto_map dynamic module loading during model initializationEPSS 1.0%CVE-2025-47277CRITICALvLLM Allows Remote Code Execution via PyNcclPipe Communication ServiceEPSS 1.0%