Local arbitrary command execution via shell-joined repository names
Published Jul 8, 2026 · Updated Jul 8, 2026
OS command injection in BentoML OpenLLM 0.6.30 allows local users to execute arbitrary commands through a malicious model repository. async_run_command joins an argument list containing an unsanitized model tag derived from repository directory names, then passes the string to create_subprocess_shell. Execution requires adding and running or serving an attacker-controlled repository; shell metacharacters in its model or version directory name run with the OpenLLM process privileges.
Summary
What happened
OS command injection in BentoML OpenLLM 0.6.30 allows local users to execute arbitrary commands through a malicious model repository. async_run_command joins an argument list containing an unsanitized model tag derived from repository directory names, then passes the string to create_subprocess_shell. Execution requires adding and running or serving an attacker-controlled repository; shell metacharacters in its model or version directory name run with the OpenLLM process privileges.
The record
- CVE
- CVE-2026-15035
- Published
- Jul 8, 2026
- Updated
- Jul 8, 2026
- Vendor
- BentoML
- Product
- OpenLLM
- Classifications
- CWE-77, CWE-74, CWE-78, T1059.004
- Attack vector
- local
- Privileges
- authenticated
Timeline
How it unfolded
- Jul 8, 2026CVE publishedPublication date reported by the CVE source.
- Jul 8, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=0.6.30
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- OpenLLM issue 1229 proof of conceptfunctional · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo