CVE-2026-71486
vLLM: Derender endpoints decode caller-supplied GenerateResponse token IDs without output bounds
Auswirkung
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.
Ein Angreifer kann die Lücke über das Netzwerk ausnutzen, mit einem normalen Benutzerkonto, ohne Zutun eines Nutzers. Bei Erfolg: geringes Risiko für Ausfälle.
Betroffene Pakete
| Ökosystem | Paket | Betroffen | Behoben in |
|---|---|---|---|
| pip | vllm | < 0.26.0 | 0.26.0 |
Betroffene Produkte · Vllm
| Produkt | Betroffene Versionen |
|---|---|
| Vllm | vor 0.26.0 |
Schwachstellenklasse
Referenzen
- NVD-Eintrag
- CVE.org-Eintrag
- GitHub-Advisory
- https://github.com/advisories/GHSA-8737-qx52-hjff
- https://github.com/vllm-project/vllm/security/advisories/GHSA-8737-qx52-hjff
- https://nvd.nist.gov/vuln/detail/CVE-2026-71486
- https://github.com/vllm-project/vllm/pull/47260
- https://github.com/vllm-project/vllm/commit/8e61b646e2d157f9b93451fa048f9c8530c8a67b
- https://github.com/vllm-project/vllm/releases/tag/v0.26.0