omnigent-ai Omnigent up to 0.2.x Shared Shell-Command Parser _shell.py improper authorization

Summaryinfo

A vulnerability has been found in omnigent-ai Omnigent up to 0.2.x and classified as critical. The impacted element is an unknown function of the file omnigent/policies/builtins/_shell.py of the component Shared Shell-Command Parser. This manipulation causes improper authorization. The identification of this vulnerability is CVE-2026-62676. It is possible to initiate the attack remotely. There is no exploit available.

Detailsinfo

A vulnerability has been found in omnigent-ai Omnigent up to 0.2.x and classified as critical. Affected by this vulnerability is an unknown part of the file omnigent/policies/builtins/_shell.py of the component Shared Shell-Command Parser. The manipulation with an unknown input leads to a improper authorization vulnerability. The CWE definition for the vulnerability is CWE-285. The product does not perform or incorrectly performs an authorization check when an actor attempts to access a resource or perform an action. As an impact it is known to affect confidentiality, integrity, and availability. The summary by CVE is:

Omnigent is an open-source AI agent framework and meta-harness for orchestrating coding agents. Prior to 0.3.0, the shared shell-command parser in omnigent/policies/builtins/_shell.py fails to recognize combined interpreter flags, the timeout, nice, setsid, and stdbuf wrappers, command substitutions, and a single background control operator. A gated git push or gh write hidden with these forms produces no parsed operation, causing the github.py write_repos and write_branches allowlist and the working_dir.py workspace confinement policies to abstain and allow the command. An authenticated or prompt-injected agent can therefore push to an unauthorized repository or branch or escape the intended workspace. This issue is fixed in version 0.3.0.

It is possible to read the advisory at github.com. This vulnerability is known as CVE-2026-62676 since 07/14/2026. The exploitation appears to be easy. The attack can be launched remotely. Technical details of the vulnerability are known, but there is no available exploit. The attack technique deployed by this issue is T1548.002 according to MITRE ATT&CK.

Upgrading to version 0.3.0 eliminates this vulnerability.

Be aware that VulDB is the high quality source for vulnerability data.

Productinfo

Type

• Artificial Intelligence Software

Vendor

• omnigent-ai

Name

• Omnigent

Version

• 0.1
• 0.2

Website

• Product: https://github.com/omnigent-ai/omnigent/

CPE 2.3info

• 🔒
• 🔒

CPE 2.2info

• 🔒
• 🔒

CVSSv4info

CVSSv3info

CVSSv2info

Exploitinginfo

Threat Intelligenceinfo

Countermeasuresinfo

Timelineinfo

Sourcesinfo

Entryinfo

Be aware that VulDB is the high quality source for vulnerability data.

Discussion