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.
Published: 2026-07-08
Score: 4.8 Medium
EPSS: 1.5% Low
KEV: No
Impact: n/a
Action: n/a
AI Analysis

Impact

The vulnerability originates in the async_run_command function of the Model Repository Directory Name Handler within bentoml OpenLLM. An attacker who can manipulate the cmd argument supplied to this function can inject shell metacharacters and cause the underlying shell to execute arbitrary commands on the host system. The weakness corresponds to CWE‑74, CWE‑77, and CWE‑78, indicating improper handling of command input, lack of sanitization, and OS command injection.

Affected Systems

The affected product is bentoml OpenLLM version 0.6.30. No other versions or vendor products are listed as affected, and application of the vulnerability is limited to this specific release.

Risk and Exploitability

The CVSS score of 4.8 denotes moderate severity, while the EPSS score of 2% indicates a low probability of exploitation in the general population. The exploit has been publicly released, yet it requires local access to the target service, and the vulnerability is not listed in the CISA KEV catalog. Consequently, an attacker who can reach the OpenLLM service locally could leverage the command injection to gain control over the underlying host.

Generated by OpenCVE AI on August 12, 2026 at 01:03 UTC.

Remediation

No vendor fix or workaround currently provided.

OpenCVE Recommended Actions

  • Upgrade bentoml OpenLLM to a version that resolves the command‑injection flaw in async_run_command.
  • If no patch is immediately available, restrict local access to the service by running it inside a secure container or with a firewall that blocks unnecessary inbound connections, and use a low‑privilege user for the service process.
  • Validate and sanitize the cmd argument before it is passed to the shell, rejecting or escaping shell metacharacters and limiting the set of allowed commands to mitigate the CWE‑74, CWE‑77, and CWE‑78 weaknesses.
  • Implement OS‑level confinement such as SELinux or AppArmor profiles to limit the system impact should an attacker succeed in executing commands within the service process.

Generated by OpenCVE AI on August 12, 2026 at 01:03 UTC.

Tracking

Sign in to view the affected projects.

Advisories

No advisories yet.

History

Wed, 08 Jul 2026 15:30:00 +0000

Type Values Removed Values Added
Metrics ssvc

{'options': {'Automatable': 'no', 'Exploitation': 'poc', 'Technical Impact': 'partial'}, 'version': '2.0.3'}


Wed, 08 Jul 2026 14:15:00 +0000

Type Values Removed Values Added
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.
Title bentoml OpenLLM Model Repository Directory Name common.py async_run_command command injection
First Time appeared Bentoml
Bentoml openllm
Weaknesses CWE-74
CWE-77
CPEs cpe:2.3:a:bentoml:openllm:*:*:*:*:*:*:*:*
Vendors & Products Bentoml
Bentoml openllm
References
Metrics cvssV2_0

{'score': 4.3, 'vector': 'AV:L/AC:L/Au:S/C:P/I:P/A:P/E:POC/RL:ND/RC:UR'}

cvssV3_0

{'score': 5.3, 'vector': 'CVSS:3.0/AV:L/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L/E:P/RL:X/RC:R'}

cvssV3_1

{'score': 5.3, 'vector': 'CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L/E:P/RL:X/RC:R'}

cvssV4_0

{'score': 4.8, 'vector': 'CVSS:4.0/AV:L/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P'}


cve-icon MITRE

Status: PUBLISHED

Assigner: VulDB

Published:

Updated: 2026-07-08T14:20:35.536Z

Reserved: 2026-07-08T07:41:07.309Z

Link: CVE-2026-15035

cve-icon Vulnrichment

Updated: 2026-07-08T14:20:32.251Z

cve-icon NVD

Status : Analyzed

Published: 2026-07-08T14:16:56.643

Modified: 2026-07-09T15:54:06.390

Link: CVE-2026-15035

cve-icon Redhat

No data.

cve-icon OpenCVE Enrichment

Updated: 2026-08-12T01:15:17Z

Weaknesses
  • CWE-74

    Improper Neutralization of Special Elements in Output Used by a Downstream Component ('Injection')

  • CWE-77

    Improper Neutralization of Special Elements used in a Command ('Command Injection')

  • CWE-78

    Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')