vLLM: VLLM through 0.29.0 fails to properly validate bad_words token indices against the model's…
vLLM
More for vLLM RSS feed for vLLM
- Severity
- Medium, CVSS 4.3
- CVSS vector
- CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:L/A:N
- Record
- CVE-2026-93989
- Affects
- vLLM
- Known exploited
- Not listed in the CISA Known Exploited Vulnerabilities catalog
- Published
- Record first published by the source
- September 19, 2026
- Source last modified
- September 28, 2026
Description
vLLM through 0.29.0 fails to properly validate bad_words token indices against the model's generation output width in SamplingParams.update_from_tokenizer(). Attackers can supply out-of-bounds token indices that corrupt logits memory of concurrent requests, causing different in-flight HTTP requests to return incorrect tokens.
Description quoted from the NVD record.