Description
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 products
vllm: vllm
References2
- github.com/vllm-project/vllm/security/advisories/GHSA-6cxc-2vcg… Vendor Advisory
- www.vulncheck.com/advisories/vllm-before-0.31.0-stale-allowed-t… Third Party Advisory
Metrics
- CVSS 3.1
-
3.7
LOW
Score source: CNA
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:N - CVSS 4.0
-
6.3
MEDIUM
Score source: CNA
CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:N/VI:L/VA:N/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X - EPSS — exploit probability
- 0% percentile: 19 · as of 9 November 2026
- CWE
- CWE-440
Could this be exploited in your environment?
A patch closes the known hole. A penetration test shows what an attacker can still reach — with proof.