Adjacent-request state corruption via unchecked token IDs
Published Sep 18, 2026 · Updated Sep 18, 2026
Memory corruption in vLLM 0.29.0 and earlier allows remote attackers to alter concurrent requests' repetition-penalty behavior. The Triton _bincount_kernel uses prompt token IDs to index a fixed vocabulary-sized presence bitset without checking the upper bound, producing an out-of-bounds write. Exploitation requires a multimodal audio request containing a token ID equal to the vocabulary size while an adjacent request uses repetition penalties.
Summary
What happened
Memory corruption in vLLM 0.29.0 and earlier allows remote attackers to alter concurrent requests' repetition-penalty behavior. The Triton _bincount_kernel uses prompt token IDs to index a fixed vocabulary-sized presence bitset without checking the upper bound, producing an out-of-bounds write. Exploitation requires a multimodal audio request containing a token ID equal to the vocabulary size while an adjacent request uses repetition penalties.
The record
- CVE
- CVE-2026-93841
- Published
- Sep 18, 2026
- Updated
- Sep 18, 2026
- Vendor
- vLLM Project
- Product
- vLLM
- Classifications
- CWE-129, T1565.003
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Sep 18, 2026CVE publishedPublication date reported by the CVE source.
- Sep 18, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=0 <=0.29.0
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Activity data is delayed. The latest report is Sep 28, 2026.
Weakness, pattern, technique
Public exploit references
No public exploit references are available in this record.
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Get started to see how Hinoki identifies affected software and validates exploitability in your environment.
Get started