LOW 2.3 NVD

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(). At

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.

References

Published: 2026-09-19 · Source: NVD · Feed updated: 2026-09-20
This low severity vulnerability with a CVSS score of 2.3 was published on 2026-09-19 via NVD.
vulnfeed aggregates 14150 vulnerabilities from NVD, CISA KEV, Ubuntu, Debian, Red Hat, Kubernetes, Exploit-DB, OSS-Security, GitHub and OpenStack — updated every 4 hours.