Is CVE-2026-15035 exploited in the wild?

No. Junglewise Threat Intelligence has no report of CVE-2026-15035 being exploited in the wild.

How severe is CVE-2026-15035?

Medium severity, with a CVSS score of 5.3, published 8 July 2026.

Which products and versions are affected?

BentoML OpenLLM 0.6.30; bentoml (PyPI) ECOSYSTEM:introduced=0,last_affected=0.6.30.

Is there a fix for CVE-2026-15035?

No fixed version is recorded yet. Check the vendor's advisory in the references below. If you run it, Junglewise drafts a mitigation that fits your setup and applies it once you approve, with senior security engineers behind it.

How is CVE-2026-15035 attacked?

It is attacked with local access, in a software library.

Am I affected by CVE-2026-15035?

Check whether you run BentoML OpenLLM or bentoml (PyPI) at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

CVE-2026-15035: bentoml OpenLLM command injection in Model Repository Directory Name Handler

CVE-2026-15035 · Severity: medium · CVSS 5.3 · Published 2026-07-08

bentoml OpenLLM is a platform used to run and deploy open-source large language models. A vulnerability exists where a specially crafted model repository can trick the system into executing unauthorized commands on the host machine. This could allow an attacker who provides a malicious model to gain control over the environment where the software is running.

Technologies: bentoml (PyPI). Vendors: BentoML, PyPI.

Quick answers

Is CVE-2026-15035 exploited in the wild?: No. Junglewise Threat Intelligence has no report of CVE-2026-15035 being exploited in the wild.
How severe is CVE-2026-15035?: Medium severity, with a CVSS score of 5.3, published 8 July 2026.
Which products and versions are affected?: BentoML OpenLLM 0.6.30; bentoml (PyPI) ECOSYSTEM:introduced=0,last_affected=0.6.30.
Is there a fix for CVE-2026-15035?: No fixed version is recorded yet. Check the vendor's advisory in the references below. If you run it, Junglewise drafts a mitigation that fits your setup and applies it once you approve, with senior security engineers behind it.
How is CVE-2026-15035 attacked?: It is attacked with local access, in a software library.
Am I affected by CVE-2026-15035?: Check whether you run BentoML OpenLLM or bentoml (PyPI) at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

Technical details

A command injection vulnerability exists in bentoml OpenLLM 0.6.30 within the `async_run_command` function in `src/openllm/common.py`. The root cause is the use of `asyncio.create_subprocess_shell` on a command string constructed by joining a list of arguments without proper sanitization. Specifically, the `bentoml_tag` is derived from directory names in a cloned model repository; if these directory names contain shell metacharacters (e.g., semicolons or backticks), they are interpreted by the shell during execution. An attacker can achieve arbitrary code execution on the victim's machine when the victim runs `openllm run` or `openllm serve` against a malicious repository. A pull request has been proposed to switch to `create_subprocess_exec`, which handles arguments as a list and avoids shell evaluation.

Affected products

bentoml OpenLLM 0.6.30

Identifiers

CVE-2026-15035
PYSEC-2026-2089

Timeline

2026-06-07: disclosed: Issue reported on GitHub repository
2026-07-07: other: Pull request with fix submitted by community member
2026-07-08: advisory: CVE published and NVD record created

References

This page as Markdown. Free to reuse under CC BY 4.0 with a link back.