Service interruption via repeated token-sequence scans
Published Sep 16, 2026 · Updated Sep 16, 2026
Algorithmic complexity in vLLM 0.29.0 and earlier allows remote attackers to interrupt inference service via crafted token sequences. ThinkingBudgetStateHolder repeatedly scans growing prompt and output token lists backward with slice comparisons to locate reasoning markers. The path requires reasoning configuration and a per-request thinking token budget; sustained costly processing can degrade availability without granting data access.
Summary
What happened
Algorithmic complexity in vLLM 0.29.0 and earlier allows remote attackers to interrupt inference service via crafted token sequences. ThinkingBudgetStateHolder repeatedly scans growing prompt and output token lists backward with slice comparisons to locate reasoning markers. The path requires reasoning configuration and a per-request thinking token budget; sustained costly processing can degrade availability without granting data access.
The record
- CVE
- CVE-2026-92365
- Published
- Sep 16, 2026
- Updated
- Sep 16, 2026
- Vendor
- vLLM Project
- Product
- vLLM
- Classifications
- T1499.003
- Attack vector
- network
- Privileges
- Unavailable
Timeline
How it unfolded
- Sep 16, 2026CVE publishedPublication date reported by the CVE source.
- Sep 16, 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=0.1
- Affected versionversion=0.10
- Affected versionversion=0.11
- Affected versionversion=0.12
- Affected versionversion=0.13
- Affected versionversion=0.14
- Affected versionversion=0.15
- Affected versionversion=0.16
- Affected versionversion=0.17
- Affected versionversion=0.18
- Affected versionversion=0.19
- Affected versionversion=0.2
- Affected versionversion=0.20
- Affected versionversion=0.21
- Affected versionversion=0.22
- Affected versionversion=0.23
- Affected versionversion=0.24
- Affected versionversion=0.25
- Affected versionversion=0.26
- Affected versionversion=0.27
- Affected versionversion=0.28
- Affected versionversion=0.29.0
- Affected versionversion=0.3
- Affected versionversion=0.4
- Affected versionversion=0.5
- Affected versionversion=0.6
- Affected versionversion=0.7
- Affected versionversion=0.8
- Affected versionversion=0.9
What conditions does exploitation require?
What is affected?
Published CVSS scores
No CVSS assessment is available in this record.
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.
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
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo