AI and data stack advisories

Severe, 6 weeks2431Projects328

2431 severe, 6 weeks · 328 projects

vLLMPYSEC-2026-4000

vLLM through 0.29.0 fails to properly validate bad_words token indices against...

vLLM

CVE-2026-93989 · Published Sep 19, 2026 · updated Sep 29, 2026

Medium4.3
Fix: upgrade to 0.30.0 or later
Source advisory

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.

Affected versions

PackageAffectedFixed in
vllm
PyPI
< 0.30.00.30.0
Details and references

More vLLM advisories

All vLLM