Upstream information
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.SUSE information
Overall state of this security issue: Does not affect SUSE products
This issue is currently rated as having moderate severity.
| CVSS detail | CNA (VulnCheck) |
|---|---|
| Base Score | 3.7 |
| Vector | CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:N |
| Attack Vector | Network |
| Attack Complexity | High |
| Privileges Required | None |
| User Interaction | None |
| Scope | Unchanged |
| Confidentiality Impact | None |
| Integrity Impact | Low |
| Availability Impact | None |
| CVSSv3 Version | 3.1 |
| CVSS detail | CNA (VulnCheck) |
|---|---|
| Base Score | 6.3 |
| 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/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 |
| Attack Vector | Network |
| Attack Complexity | Low |
| Attack Requirements | Present |
| Privileges Required | None |
| User Interaction | None |
| Vulnerable System Confidentiality Impact | None |
| Vulnerable System Integrity Impact | Low |
| Vulnerable System Availability Impact | None |
| Subsequent System Confidentiality Impact | None |
| Subsequent System Integrity Impact | None |
| Subsequent System Availability Impact | None |
| CVSSv4 Version | 4.0 |
SUSE Timeline for this CVE
CVE page created: Mon Sep 21 20:50:26 2026CVE page last modified: Wed Sep 23 19:45:10 2026