CVE-2026-73559: CWE-400: Uncontrolled Resource Consumption in vllm-project vllm
CVE-2026-73559 is a medium severity vulnerability in vllm, an inference and serving engine for large language models. Versions from 0.19.0 up to but not including 0.26.0 allow an authenticated API client to send a CompletionRequest with an unbounded list of prompts. This leads to uncontrolled resource consumption, exhausting CPU, memory, async scheduling capacity, engine request slots, and response buffering. The issue is fixed in version 0.26.0.
AI Analysis
Technical Summary
The vulnerability arises because the /v1/completions CompletionRequest.prompt field accepts an unbounded list of strings or lists of integers. The functions prompt_to_seq() and OnlineRenderer.preprocess_completion() expand every element, and the serving code creates one engine generator and response slot per prompt. This design flaw allows an authenticated API client to exhaust critical system resources with a single request. The flaw affects vllm versions >=0.19.0 and <0.26.0 and is addressed in version 0.26.0.
Potential Impact
An authenticated API client can cause denial of service by exhausting CPU, memory, asynchronous scheduling capacity, engine request slots, and response buffering. This impacts availability but does not affect confidentiality or integrity.
Mitigation Recommendations
Upgrade to vllm version 0.26.0 or later, where this issue is fixed. Patch status is confirmed by the version range and fix version stated in the description. No other mitigation is indicated.
CVE-2026-73559: CWE-400: Uncontrolled Resource Consumption in vllm-project vllm
Description
CVE-2026-73559 is a medium severity vulnerability in vllm, an inference and serving engine for large language models. Versions from 0.19.0 up to but not including 0.26.0 allow an authenticated API client to send a CompletionRequest with an unbounded list of prompts. This leads to uncontrolled resource consumption, exhausting CPU, memory, async scheduling capacity, engine request slots, and response buffering. The issue is fixed in version 0.26.0.
CVSS v3.1
Score 6.5medium
Affected software
vllm-project
vllm
Weaknesses
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
The vulnerability arises because the /v1/completions CompletionRequest.prompt field accepts an unbounded list of strings or lists of integers. The functions prompt_to_seq() and OnlineRenderer.preprocess_completion() expand every element, and the serving code creates one engine generator and response slot per prompt. This design flaw allows an authenticated API client to exhaust critical system resources with a single request. The flaw affects vllm versions >=0.19.0 and <0.26.0 and is addressed in version 0.26.0.
Potential Impact
An authenticated API client can cause denial of service by exhausting CPU, memory, asynchronous scheduling capacity, engine request slots, and response buffering. This impacts availability but does not affect confidentiality or integrity.
Mitigation Recommendations
Upgrade to vllm version 0.26.0 or later, where this issue is fixed. Patch status is confirmed by the version range and fix version stated in the description. No other mitigation is indicated.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- GitHub_M
- Date Reserved
- 2026-08-12T20:53:46.380Z
- Cvss Version
- 3.1
- State
- PUBLISHED
Threat ID: 6a7de5d0bf8831d5396651b2
Added to database: 08/13/2026, 15:42:08 UTC
Last enriched: 08/21/2026, 13:44:48 UTC
Last updated: 09/26/2026, 13:47:48 UTC
Views: 54
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.