CVE-2026-15035: Command Injection Vulnerability in bentoml OpenLLM 0.6.30

bentoml Updated 18 Jul 2026

Summary

08/07/2026
No i
High
7.8

CVE-2026-15035: A vulnerability was found in bentoml OpenLLM 0.6.30. Affects bentoml versions < 0.6.30. No fix is published. How to fix ↓

Free scan

Check if this vulnerability affects your application

Upload a manifest or SBOM and we'll show whether you're affected, plus every other risky package in the same scan.

Check my app free

No signup required · Results in about 60 seconds

Upload your dependency manifest or SBOM

Drag & drop your file here or

Java Javascript PHP Python Go Rust Ruby Dart C/C++ Elixir CycloneDX SPDX

Upload a supported dependency manifest or SBOM. No installation or source-code access required.

See supported files and SBOM formats
SBOM sbom.json · bom.json · bom.xml · *.spdx.json · *.cdx.json · *.cdx.xml
Java pom.xml · gradle.lockfile · buildscript-gradle.lockfile
Javascript package-lock.json · yarn.lock · pnpm-lock.yaml
PHP composer.lock
Python poetry.lock · requirements.txt · Pipfile.lock
Go go.mod
Rust Cargo.lock
Ruby Gemfile.lock
Dart pubspec.lock
C/C++ conan.lock
Elixir mix.lock
Enter your work email to receive your report link.

Verify your email to view the full report and start 30 days of continuous monitoring. No credit card required.

Sponsored Devnack Penetration testing for web, API and mobile Manual testing by engineers who build software, not an auditor's checklist. Trusted by teams at Swift and Google Talk to Devnack

Background

bentoml is an open-source framework designed for building and deploying machine learning models. It provides a user-friendly interface for managing model repositories and facilitates the deployment of models as APIs. The specific version affected, OpenLLM 0.6.30, has a vulnerability that allows for command injection through improper handling of command arguments.

Vulnerability Detail

A command injection vulnerability exists in the async_run_command function located in src/openllm/common.py of the bentoml OpenLLM package. This vulnerability arises from the manipulation of the 'cmd' argument, which can allow an attacker to execute arbitrary commands on the host system. The requirement for local access to exploit this vulnerability increases the risk for users who may have untrusted local users or processes. The ramifications include potential unauthorized access to system resources, data leakage, and further exploitation of the system.

How To Fix

No fixed version is published for this vulnerability.

Tip — Not sure whether your app is affected? Vulert can check the versions your app actually runs. Scan free →

Workaround

As a temporary workaround, avoid using the async_run_command function with untrusted input. Validate and sanitize all inputs to the 'cmd' argument to prevent command injection.

Conclusion

The command injection vulnerability in bentoml OpenLLM 0.6.30 poses significant risks to users, particularly those with untrusted local environments. It is crucial to update to a patched version to safeguard against potential exploits. Users are encouraged to monitor their applications for vulnerabilities using tools like Vulert.

See every vulnerability recorded for bentoml →

Share this vulnerability

FAQ

The CVSS score of this vulnerability is 7.8, indicating a high severity level.

No, this vulnerability requires local access to exploit.

The affected version is bentoml OpenLLM 0.6.30 and earlier.

You can use Vulert's playground at Vulert Scanner to check if your application is affected by this vulnerability without needing to sign up.

If you cannot update the package, ensure to validate and sanitize all inputs to the 'cmd' argument to mitigate the risk of command injection.

Related vulnerabilities

Recent vulnerabilities recorded for bentoml.

How To Fix

No fixed version is published for this vulnerability.

Tip — Not sure whether your app is affected? Vulert can check the versions your app actually runs. Scan free →

Subscribe to Vulert on Telegram
Daily digest of new CVEs, critical and high severity, affected packages and fixes — plus a weekly roundup.
Join the channel →
Help improve this record
Report an issue or send feedback