Description (CNA)
vLLM before 0.31.0 contains a cross-request mask leak in InputBatch.condense() that allows remote attackers to constrain other clients' outputs by leaving stale allowed_token_ids rows. Attackers can submit concurrent constrained generate requests, including via unauthenticated /invocations, so recycled batch slots apply their token allowlist to victims' unrestricted requests.
Affected (CNA)
| Vendor / product | Versions |
|---|---|
| vllm-project / vllm | affected 0 before 0.31.0; unaffected 0.31.0 |
CWE
CWE-440