CVE-2026-92220: Resource Consumption in vllm-project vLLM
A vulnerability was found in vllm-project vLLM 0.26.0/0.27.0. Affected is the function MoRIIOConnectorScheduler.request_finished/MoRIIOConnectorWorker.get_finished/MoRIIOWrapper._handle_release_message of the file vllm/distributed/kv_transfer/kv_connector/v1/moriio/moriio_connector.py of the component MoRIIO Acknowledgement Handler. Performing a manipulation of the argument request_id/kv_transfer_params results in resource consumption. It is possible to initiate the attack remotely. The project was informed of the problem early through a pull request but has not reacted yet.
AI Analysis
Technical Summary
This vulnerability in vllm-project vLLM 0.26.0 and 0.27.0 involves the MoRIIO Acknowledgement Handler's functions MoRIIOConnectorScheduler.request_finished, MoRIIOConnectorWorker.get_finished, and MoRIIOWrapper._handle_release_message. By manipulating the arguments request_id or kv_transfer_params, an attacker can cause excessive resource consumption remotely. The issue was reported early via a pull request, but the project has not issued a fix or official response.
Potential Impact
An unauthenticated remote attacker can trigger resource consumption in the affected vLLM versions by manipulating specific function arguments. This may degrade system performance or availability but does not indicate privilege escalation, data disclosure, or code execution. No known exploits are reported in the wild.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Since no official fix or patch is available and the vendor has not reacted, users should monitor for updates from the vllm-project. Until a fix is released, consider limiting exposure of the affected component to untrusted networks if possible.
CVE-2026-92220: Resource Consumption in vllm-project vLLM
Description
A vulnerability was found in vllm-project vLLM 0.26.0/0.27.0. Affected is the function MoRIIOConnectorScheduler.request_finished/MoRIIOConnectorWorker.get_finished/MoRIIOWrapper._handle_release_message of the file vllm/distributed/kv_transfer/kv_connector/v1/moriio/moriio_connector.py of the component MoRIIO Acknowledgement Handler. Performing a manipulation of the argument request_id/kv_transfer_params results in resource consumption. It is possible to initiate the attack remotely. The project was informed of the problem early through a pull request but has not reacted yet.
CVSS v4.0
Score 6.9medium
Affected software
vllm-project
vLLM
cpe:2.3:a:vllm-project:vllm:*:*:*:*:*:*:*:*Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
This vulnerability in vllm-project vLLM 0.26.0 and 0.27.0 involves the MoRIIO Acknowledgement Handler's functions MoRIIOConnectorScheduler.request_finished, MoRIIOConnectorWorker.get_finished, and MoRIIOWrapper._handle_release_message. By manipulating the arguments request_id or kv_transfer_params, an attacker can cause excessive resource consumption remotely. The issue was reported early via a pull request, but the project has not issued a fix or official response.
Potential Impact
An unauthenticated remote attacker can trigger resource consumption in the affected vLLM versions by manipulating specific function arguments. This may degrade system performance or availability but does not indicate privilege escalation, data disclosure, or code execution. No known exploits are reported in the wild.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Since no official fix or patch is available and the vendor has not reacted, users should monitor for updates from the vllm-project. Until a fix is released, consider limiting exposure of the affected component to untrusted networks if possible.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- VulDB
- Date Reserved
- 2026-09-15T18:42:00.653Z
- Cvss Version
- 4.0
- State
- PUBLISHED
Threat ID: 6aa9ffaf55bf5e2cf5e1933c
Added to database: 09/16/2026, 02:32:15 UTC
Last enriched: 09/16/2026, 02:46:31 UTC
Last updated: 09/16/2026, 03:03:35 UTC
Views: 6
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.