Vulnerability · Published Sep 16, 2026 · Assigned by VulDB
CVE-2026-92365vllm-project vllm thinking_budget_state.py algorithmic complexity
Medium 4.3
In plain English
A medium-severity security flaw in vllm from vllm-project. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 0.5% (higher than 44% of all known vulnerabilities).
Severity (CVSS 3.1)4.3Medium
Exploit odds (30 days)0.5%top 55.6% of all CVEs
Exploited in the wildNo reportsCISA SSVC: none
Attack toolingNoneno public tooling known
Official description
A vulnerability was found in vllm-project vllm up to 0.29.0. Affected by this issue is some unknown functionality of the file vllm/v1/sample/thinking_budget_state.py. The manipulation results in inefficient algorithmic complexity. It is possible to launch the attack remotely. The pull request to fix this issue awaits acceptance.
Affected products (as reported)
| Vendor | Product | Versions |
|---|---|---|
| vllm-project | vllm | 0.10.20.30.40.50.60.70.8 |
Weakness: CWE-407, CWE-404 · Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L/E:X/RL:X/RC:R
References
- VDB-405451 | vllm-project vllm thinking_budget_state.py algorithmic complexity vdb-entry
- VDB-405451 | CTI Indicators (IOB, IOC, TTP, IOA) signature, permissions-required
- CVE-2026-92365 | CVE Analysis and Report third-party-advisory
- Submit #935016 | vLLM Project vLLM >=0.26.0 Inefficient Algorithmic Complexity third-party-advisory
- https://github.com/vllm-project/vllm/pull/51133 issue-tracking, patch
- https://github.com/vllm-project/vllm/ product