CVE-2026-15035: Command Injection in bentoml OpenLLM
A vulnerability was found in bentoml OpenLLM 0.6.30. This affects the function async_run_command of the file src/openllm/common.py of the component Model Repository Directory Name Handler. Performing a manipulation of the argument cmd results in command injection. Attacking locally is a requirement. The exploit has been made public and could be used. The project was informed of the problem early through an issue report but has not responded yet.
AI Analysis
Technical Summary
This vulnerability in bentoml OpenLLM 0.6.30 allows an attacker with local access to perform command injection by manipulating the cmd argument in the async_run_command function of src/openllm/common.py. The affected component is the Model Repository Directory Name Handler. The vulnerability has been publicly disclosed, and the project has not yet issued a fix or official remediation guidance. The CVSS 4.0 vector indicates low attack vector (local), low attack complexity, no user interaction, and partial impacts on confidentiality, integrity, and availability.
Potential Impact
An attacker with local access can exploit this vulnerability to execute arbitrary commands on the affected system via the vulnerable async_run_command function. This could lead to unauthorized command execution, potentially compromising system integrity and availability. However, exploitation requires local privileges, limiting the attack surface.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Since the vendor has not responded or released a fix, users should restrict local access to trusted users only and monitor for any updates from bentoml regarding a patch or official mitigation.
CVE-2026-15035: Command Injection in bentoml OpenLLM
Description
A vulnerability was found in bentoml OpenLLM 0.6.30. This affects the function async_run_command of the file src/openllm/common.py of the component Model Repository Directory Name Handler. Performing a manipulation of the argument cmd results in command injection. Attacking locally is a requirement. The exploit has been made public and could be used. The project was informed of the problem early through an issue report but has not responded yet.
CVSS v4.0
Score 4.8medium
Affected software
cpe:2.3:a:bentoml:openllm:*:*:*:*:*:*:*:*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 bentoml OpenLLM 0.6.30 allows an attacker with local access to perform command injection by manipulating the cmd argument in the async_run_command function of src/openllm/common.py. The affected component is the Model Repository Directory Name Handler. The vulnerability has been publicly disclosed, and the project has not yet issued a fix or official remediation guidance. The CVSS 4.0 vector indicates low attack vector (local), low attack complexity, no user interaction, and partial impacts on confidentiality, integrity, and availability.
Potential Impact
An attacker with local access can exploit this vulnerability to execute arbitrary commands on the affected system via the vulnerable async_run_command function. This could lead to unauthorized command execution, potentially compromising system integrity and availability. However, exploitation requires local privileges, limiting the attack surface.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Since the vendor has not responded or released a fix, users should restrict local access to trusted users only and monitor for any updates from bentoml regarding a patch or official mitigation.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- VulDB
- Date Reserved
- 2026-07-08T07:41:07.309Z
- Cvss Version
- 4.0
- State
- PUBLISHED
- Remediation Level
- null
Threat ID: 6a4e5b30c9d9e3dbe33e5256
Added to database: 07/08/2026, 14:14:08 UTC
Last enriched: 07/08/2026, 14:29:20 UTC
Last updated: 07/09/2026, 02:12:27 UTC
Views: 16
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.