LOWCVSS 3.1
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 2026-09-19 · last modified 2026-09-19
← Get alerted the moment a CVE hits your gear — subscribe freeNcerio by BeyondNets · data from NVD, CISA KEV, EPSS.