Vulnerability 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.
CVSS Score
LOW
Related Weaknesses (CWE)
References
- https://github.com/vllm-project/vllm
- https://github.com/vllm-project/vllm/blob/98dff2a81d747d1dba01a47f939f48c3526d42
- https://github.com/vllm-project/vllm/blob/98dff2a81d747d1dba01a47f939f48c3526d42
- https://github.com/vllm-project/vllm/pull/48824
- https://www.vulncheck.com/advisories/vllm-through-0.29.0-cross-request-logits-co
FAQ
What is CVE-2026-93989?
CVE-2026-93989 is a vulnerability with a CVSS score of 3.1 (LOW). 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 i...
How severe is CVE-2026-93989?
CVE-2026-93989 has been rated LOW with a CVSS base score of 3.1/10. Review the CVSS metrics above for detailed severity breakdown.
Is there a patch for CVE-2026-93989?
Check the references section above for vendor advisories and patch information. Review vendor security bulletins for remediation guidance.