CVE-2026-105752: falha de baixa gravidade em vllm-project vllm
vLLM: Harmony tool continuations drop `cache_salt` — restoring a cross-tenant prefix-cache membership oracle
Publicada em · Atualizada em
Aviso por e-mail quando ela entrar no KEV, ganhar PoC pública ou subir de nota.
8Vexday Risk Score
Sem sinal de exploração. Nenhum artefato público de exploração conhecido até agora.
ssvc Trackcvss 3.1epss 0.2%
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, Harmony tool continuations submitted through "POST /v1/responses" requests rebuild the next-turn engine input without preserving the cache_salt value, placing the continuation prefix in the global unsalted cache namespace even when the caller enabled salting. On deployments with prefix caching enabled, which is the default, an authenticated tenant who can reconstruct a victim's low-entropy post-tool history can submit the same continuation and use the cached_tokens_per_turn count to determine whether the prefix was previously processed, defeating the intended tenant isolation of salted prefix caching. This issue is fixed in version 0.30.0.
CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:L/A:N
Produtos afetados
vllm-project · vllmCVEs relacionadas — vllm-project vllm
No mesmo produto, das mais perigosas para as menos.
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 1.5%CVE-2026-48746CRITICALvLLM: OpenAI auth bypassEPSS 1.2%CVE-2025-47277CRITICALvLLM Allows Remote Code Execution via PyNcclPipe Communication ServiceEPSS 1.0%CVE-2026-22807HIGHvLLM affected by RCE via auto_map dynamic module loading during model initializationEPSS 1.0%
Referências
https://github.com/vllm-project/vllm/commit/6a2a2bb02b563b83f946012959fd3927984d072ahttps://github.com/vllm-project/vllm/pull/50195https://github.com/vllm-project/vllm/pull/51818https://github.com/vllm-project/vllm/releases/tag/v0.30.0https://github.com/vllm-project/vllm/security/advisories/GHSA-935w-9g4m-p28p