CVE-2026-93989
vLLM through 0.29.0 Cross-Request Logits Corruption via bad_words
Description
vLLM through 0.29.0 fails to properly validate bad_words token indices against the model's generation output width in SamplingParams.update_from_tokenizer(). Attackers can supply out-of-bounds token indices that corrupt logits memory of concurrent requests, causing different in-flight HTTP requests to return incorrect tokens.
INFO
Published Date :
Sept. 19, 2026, 11:17 p.m.
Last Modified :
Sept. 19, 2026, 11:17 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 | LOW | 83251b91-4cc7-4094-a5c7-464a1b83ea10 | ||||
| CVSS 4.0 | LOW | [email protected] |
Solution
- Update vLLM to version 0.30.0 or later.
- Apply vendor patches for the sampling validation vulnerability.
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-2026-93989.
CWE - Common Weakness Enumeration
While CVE identifies
specific instances of vulnerabilities, CWE categorizes the common flaws or
weaknesses that can lead to vulnerabilities. CVE-2026-93989 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-2026-93989
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-2026-93989 vulnerability anywhere in the article.
The following table lists the changes that have been made to the
CVE-2026-93989 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. 19, 2026
Action Type Old Value New Value Added Description vLLM through 0.29.0 fails to properly validate bad_words token indices against the model's generation output width in SamplingParams.update_from_tokenizer(). Attackers can supply out-of-bounds token indices that corrupt logits memory of concurrent requests, causing different in-flight HTTP requests to return incorrect tokens. Added CVSS V4.0 AV:N/AC:H/AT:P/PR:L/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:L/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-2026-93989.json">CVE-2026-93989</a> Added Reference https://github.com/vllm-project/vllm Added Reference https://github.com/vllm-project/vllm/blob/98dff2a81d747d1dba01a47f939f48c3526d4206/vllm/sampling_params.py#L694-L753 Added Reference https://github.com/vllm-project/vllm/blob/98dff2a81d747d1dba01a47f939f48c3526d4206/vllm/v1/worker/gpu/sample/bad_words.py Added Reference https://github.com/vllm-project/vllm/pull/48824 Added Reference https://www.vulncheck.com/advisories/vllm-through-0.29.0-cross-request-logits-corruption-via-bad-words