CVE-2026-93989
vLLM through 0.29.0 Cross-Request Logits Corruption via bad_words
Using vllm by vllm-project?
Get instant alerts when new vulnerabilities affect vllm - before attackers find them.
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.
Remediation
No guide yetNo remediation guidance has been written for this CVE yet. What the record does show:
Patch and advisory references
References (5)
SSVC — Action Prioritization
SSVC signals action urgency (what to patch first), separate from CVSS which measures severity.
CVSS
- Attack Vector
- NETWORK
- Complexity
- LOW
- Privileges
- LOW
- User Interaction
- NONE
- Scope
- UNCHANGED
- Confidentiality
- NONE
- Integrity
- LOW
- Availability
- NONE
Quick Info
Get alerted
Stop reading CVE feeds looking for your own stack
Track the products you run and VulnTracker tells you when a new CVE affects them — with what is known about fixing it, and nothing about the rest.