CVE-2026-71486Medium· 4.3▾ TwilightPoC availablevLLM 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, choice…
▾ Twilight zone — High severity, or a signal on a lesser flaw
impact 23.7 · likelihood 0.1 · exploitation 12
A public proof-of-concept already exists for this vulnerability — see Exploit availability below.
Exploit-prediction probability, daily snapshots since Sep 4.
Disclosure to exploitation, from the record and what we observed since indexing it.
Disclosed via NVD
0.3%
0.3% → 0.5%
Last analysed / modified upstream
Exploit / PoC code exists
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.
vllm < 0.26.0Upgrade past the affected range:
vllm 0.26.0Affected packages:
vllm < 0.26.0Patched in:
vllm 0.26.0Source: https://github.com/advisories/GHSA-8737-qx52-hjff
Field changes observed since this record was first indexed.
Connected by shared product, vendor, weakness, or advisory.
CVE-2026-69147Medium· 6.5vLLM is an inference and serving engine for large language models
CVE-2026-73559Medium· 6.5vLLM is an inference and serving engine for large language models
CVE-2026-105760Medium· 5.3vLLM is an inference and serving engine for large language models
CVE-2026-73556Medium· 5.3vLLM is an inference and serving engine for large language models
CVE-2026-114055High· 7.5vLLM 0.7.3 before 0.31.0 DoS via Unvalidated mm_processor_kwargs
CVE-2026-105758Medium· 5.3vLLM is an inference and serving engine for large language models