Przejdź do treści
CodeAuditAgent

CVE-2026-93840

vLLM before 0.29.0 validates allowed_token_ids against tokenizer length instead of model output logits width in SamplingParams._validate_allowed_token_ids(). Attackers can supply token IDs above the output vocabulary that pass validation, causing LogitBiasState to corrupt GPU logits state and allow concurrent requests to sample tokens outside their allowlists.

Słabość

vLLM before 0.29.0 validates allowed_token_ids against tokenizer length instead of model output logits width in SamplingParams._validate_allowed_token_ids(). Attackers can supply token IDs above the output vocabulary that pass validation, causing LogitBiasState to corrupt GPU logits state and allow concurrent requests to sample tokens outside their allowlists.

Źródła

Znajdź błąd, zanim zrobi to atakujący.

Zaloguj się przez GitHub i uruchom pierwszy audyt w niecałą minutę. Plan darmowy nie wymaga karty kredytowej.