CVE-2026-93989
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.
- Published Sep 19, 2026
- CVSS 2.3 low
- 0.2% chance of exploitation in the next 30 days (EPSS)
- A fix is available