CVE-2026-7141: Uninitialized Resource in vllm
A vulnerability was found in vllm up to 0.19.0. The affected element is the function has_mamba_layers of the file vllm/v1/kv_cache_interface.py of the component KV Block Handler. Performing a manipulation results in uninitialized resource. It is possible to initiate the attack remotely. The attack is considered to have high complexity. The exploitability is described as difficult. The exploit has been made public and could be used. The patch is named 1ad67864c0c20f167929e64c875f5c28e1aad9fd. To fix this issue, it is recommended to deploy a patch.
AI Analysis
Technical Summary
This vulnerability affects the vllm project versions up to 0.19.0 in the function has_mamba_layers located in vllm/v1/kv_cache_interface.py. The flaw is due to an uninitialized resource that can be manipulated remotely. The attack complexity is high, and no privileges or user interaction are required. The vulnerability has a CVSS 4.0 base score of 6.3, indicating medium severity. Although an exploit is publicly available, exploitation is considered difficult. A patch exists (commit 1ad67864c0c20f167929e64c875f5c28e1aad9fd) to fix the issue.
Potential Impact
Successful exploitation could lead to improper handling of uninitialized resources in the KV Block Handler, potentially causing unexpected behavior or resource misuse. The vulnerability does not require privileges or user interaction but has high attack complexity and low impact on confidentiality, integrity, and availability. No known exploits in the wild have been reported.
Mitigation Recommendations
A patch identified by commit 1ad67864c0c20f167929e64c875f5c28e1aad9fd is available and should be deployed to remediate this vulnerability. Since the vendor advisory or official remediation level is not explicitly provided, users should verify the patch status with the official vllm project repository or vendor advisory before deployment.
CVE-2026-7141: Uninitialized Resource in vllm
Description
A vulnerability was found in vllm up to 0.19.0. The affected element is the function has_mamba_layers of the file vllm/v1/kv_cache_interface.py of the component KV Block Handler. Performing a manipulation results in uninitialized resource. It is possible to initiate the attack remotely. The attack is considered to have high complexity. The exploitability is described as difficult. The exploit has been made public and could be used. The patch is named 1ad67864c0c20f167929e64c875f5c28e1aad9fd. To fix this issue, it is recommended to deploy a patch.
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
This vulnerability affects the vllm project versions up to 0.19.0 in the function has_mamba_layers located in vllm/v1/kv_cache_interface.py. The flaw is due to an uninitialized resource that can be manipulated remotely. The attack complexity is high, and no privileges or user interaction are required. The vulnerability has a CVSS 4.0 base score of 6.3, indicating medium severity. Although an exploit is publicly available, exploitation is considered difficult. A patch exists (commit 1ad67864c0c20f167929e64c875f5c28e1aad9fd) to fix the issue.
Potential Impact
Successful exploitation could lead to improper handling of uninitialized resources in the KV Block Handler, potentially causing unexpected behavior or resource misuse. The vulnerability does not require privileges or user interaction but has high attack complexity and low impact on confidentiality, integrity, and availability. No known exploits in the wild have been reported.
Mitigation Recommendations
A patch identified by commit 1ad67864c0c20f167929e64c875f5c28e1aad9fd is available and should be deployed to remediate this vulnerability. Since the vendor advisory or official remediation level is not explicitly provided, users should verify the patch status with the official vllm project repository or vendor advisory before deployment.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- VulDB
- Date Reserved
- 2026-04-26T19:38:00.529Z
- Cvss Version
- 4.0
- State
- PUBLISHED
- Remediation Level
- null
Threat ID: 69ef99a0ba26a39fba48b577
Added to database: 4/27/2026, 5:15:12 PM
Last enriched: 4/27/2026, 5:30:09 PM
Last updated: 4/27/2026, 6:30:50 PM
Views: 3
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.