CVE-2026-93840
vLLM before 0.29.0 Cross-Request Logits Corruption via allowed_token_ids
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.
INFO
Published Date :
Sept. 18, 2026, 8:17 p.m.
Last Modified :
Sept. 18, 2026, 8:17 p.m.
Remotely Exploit :
Yes !
Source :
[email protected]
CVSS Scores
| Score | Version | Severity | Vector | Exploitability Score | Impact Score | Source |
|---|---|---|---|---|---|---|
| CVSS 3.1 | LOW | 83251b91-4cc7-4094-a5c7-464a1b83ea10 | ||||
| CVSS 3.1 | LOW | [email protected] | ||||
| CVSS 4.0 | MEDIUM | 83251b91-4cc7-4094-a5c7-464a1b83ea10 | ||||
| CVSS 4.0 | MEDIUM | [email protected] |
Solution
- Update vLLM to version 0.29.0 or later.
- Apply vendor patches as they become available.
- Validate token ID handling in sampling.
References to Advisories, Solutions, and Tools
Here, you will find a curated list of external links that provide in-depth
information, practical solutions, and valuable tools related to
CVE-2026-93840.
CWE - Common Weakness Enumeration
While CVE identifies
specific instances of vulnerabilities, CWE categorizes the common flaws or
weaknesses that can lead to vulnerabilities. CVE-2026-93840 is
associated with the following CWEs:
Common Attack Pattern Enumeration and Classification (CAPEC)
Common Attack Pattern Enumeration and Classification
(CAPEC)
stores attack patterns, which are descriptions of the common attributes and
approaches employed by adversaries to exploit the CVE-2026-93840
weaknesses.
We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).
Results are limited to the first 15 repositories due to potential performance issues.
The following list is the news that have been mention
CVE-2026-93840 vulnerability anywhere in the article.
The following table lists the changes that have been made to the
CVE-2026-93840 vulnerability over time.
Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.
-
New CVE Received by [email protected]
Sep. 18, 2026
Action Type Old Value New Value Added 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. Added CVSS V4.0 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 Added CVSS V3.1 AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:N Added CWE CWE-129 Added Affected New affected value received. <a href="https://github.com/CVEProject/cvelistV5/blob/main/cves/2026/93xxx/CVE-2026-93840.json">CVE-2026-93840</a> Added Reference https://github.com/vllm-project/vllm Added Reference https://github.com/vllm-project/vllm/blob/v0.28.0/vllm/sampling_params.py#L881-L903 Added Reference https://github.com/vllm-project/vllm/blob/v0.28.0/vllm/v1/worker/gpu/sample/logit_bias.py#L179-L191 Added Reference https://github.com/vllm-project/vllm/commit/5b0e5b69ac1a3884a6479c9537789c95263cc804 Added Reference https://github.com/vllm-project/vllm/pull/49080 Added Reference https://www.vulncheck.com/advisories/vllm-before-0.29.0-cross-request-logits-corruption-via-allowed-token-ids