Skip to main content
VulnerabilityPublished

CVE-2026-15035: bentoml OpenLLM · Command Injection

Affects bentoml OpenLLMSource CVE Database V5

0
Compare

Public exploit available · CVSS 4.8 Medium.

Data as of 21 Nov 2026, 17:35 UTC

CVSS 4.0 base score
4.8Medium
How severe the flaw is on the 0–10 CVSS scale.

Thin evidence

One scorer or none
CVSS scores by source
CNA (VulDB)CVSS 4.04.8
CNA (VulDB)CVSS 3.15.3
CNA (VulDB)CVSS 3.05.3
CNA (VulDB)CVSS 2.04.3
EPSS
2.2% chance of exploitation in 30 days – higher than 83% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
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

Exploitation evidence

  1. Disclosed: evidence found.

    CVE published 8 Jul 2026

  2. Detectable: no evidence on record.

    No public nuclei template indexed

  3. Weaponized: evidence found.

    CVSS exploit maturity: proof of concept public

  4. Exploited in the wild: no evidence on record.

    Not in CISA KEV and no source reports exploitation

  5. Observed by OffSeq Mirage: no evidence on record.

    No attack traffic recorded by OffSeq Mirage sensors

A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), CVSS vector, the Metasploit, Exploit-DB and nuclei-templates index as of 21 Nov 2026.

What to do

Affected software

ProductAffectedFixed in
bentomlOpenLLMAffected
  • =0.6.30
Fixed in–
PyPIbentoml-openllmpkg:pypi/bentoml-openllmOther threatsAffected
  • =0.6.30
Fixed in–

CPE configurations (1)

  • cpe:2.3:a:bentoml:openllm:*:*:*:*:*:*:*:*

Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.

AI-suggested

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.

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.

References

Community reviews

Loading reviews…