Command Injection in OpenLLM Model Repository by Bentoml
CVE-2026-15035

4.8MEDIUM

Key Information:

Vendor

Bentoml

Status
Openllm
Vendor
CVE Published:
8 July 2026

Badges

👾 Exploit Exists🟡 Public PoC

What is CVE-2026-15035?

A command injection vulnerability has been identified in the OpenLLM 0.6.30, specifically within the async_run_command function located in src/openllm/common.py. This flaw allows an attacker to manipulate the cmd argument, potentially leading to unauthorized command execution on affected systems. Currently, the exploitation requires local access, and the issue has been publicly disclosed. Despite prior notification to the project maintainers, no response has been recorded.

Affected Version(s)

OpenLLM 0.6.30

Exploit Proof of Concept (PoC)

PoC code is written by security researchers to demonstrate the vulnerability can be exploited. PoC code is also a key component for weaponization which could lead to ransomware.

CVE-2026-15035 - Proof of Concept

References

https://vuldb.com/vuln/376786
vdb-entrytechnical-description
https://vuldb.com/vuln/376786/cti
signaturepermissions-required
https://vuldb.com/cve/CVE-2026-15035
third-party-advisory

CVSS V4

Score:
4.8
Severity:
MEDIUM
Confidentiality:
Low
Integrity:
Low
Availability:
Low
Attack Vector:
Local
Attack Complexity:
Low
Attack Required:
None
Privileges Required:
Undefined
User Interaction:
None

Timeline

  • 🟡

    Public PoC available

  • 👾

    Exploit known to exist

  • Vulnerability published

  • Vulnerability Reserved

Credit

geochen (VulDB User)
VulDB CNA Team
.