vLLM before 0.29.0 Cross-Request Logits Corruption via allowed_token_ids

Advisories

vLLM before 0.29.0 Cross-Request Logits Corruption via allowed_token_ids

severity: medium
date: 9/18/2026
Affecting: vllm >= 0, < 0.29.0
CVE: CVE-2026-93840
CWE: CWE-129 Improper Validation of Array Index
CVSS: 6.3
CVSS V4 Vector: CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:N/VI:L/VA:N/SC:N/SI:N/SA:N
References: https://github.com/vllm-project/vllm/pull/49080
https://github.com/vllm-project/vllm
https://github.com/vllm-project/vllm/commit/5b0e5b69ac1a3884a6479c9537789c95263cc804
https://github.com/vllm-project/vllm/blob/v0.28.0/vllm/sampling_params.py#L881-L903
https://github.com/vllm-project/vllm/blob/v0.28.0/vllm/v1/worker/gpu/sample/logit_bias.py#L179-L191
Credit: Mingkai Yu, Jiapeng Li, Jiajia Liu
Description: vLLM before 0.29.0 validates allowed_token_ids against tokenizer length instead of model output logits width in SamplingParams._validate_allowed_token_ids(). Attackers can supply token IDs above the output vocabulary that pass validation, causing LogitBiasState to corrupt GPU logits state and allow concurrent requests to sample tokens outside their allowlists.

Ready to get Started?

Explore VulnCheck, a next-generation Cyber Threat Intelligence platform, which provides exploit and vulnerability intelligence to help you prioritize and remediate vulnerabilities that matter.

Vulnerability Prioritization
Prioritize vulnerabilities that matter based on the threat landscape and defer vulnerabilities that don't.
Early Warning System
Real-time alerting of changes in the vulnerability landscape so that you can take action before the attacks start.

Schedule a Demo