# CVE-2026-62676

## Summary

- **CVE ID:** CVE-2026-62676
- **Severity:** HIGH
- **CVSS Score:** 7.1 (CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:N)
- **CWE:** CWE-184
- **Published:** Aug 21, 2026
- **Last Modified:** Aug 26, 2026

## Description

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.

## Affected Products

- omnigent-ai — omnigent (< 0.3.0)

## References

- [CNA](https://github.com/omnigent-ai/omnigent/security/advisories/GHSA-7mqg-cx4g-x2rf)
- [CNA](https://github.com/omnigent-ai/omnigent/pull/389)
- [CNA](https://github.com/omnigent-ai/omnigent/commit/1a05b7b139ef504bf2be89bf37918abe104fb95c)
- [CNA](https://github.com/omnigent-ai/omnigent/releases/tag/v0.3.0)

## Exploitation Prediction (EPSS)

- **EPSS Score:** 0.29%
- **EPSS Percentile:** 21.9

---
_Exported from OnDuty AI Vulnerability Intelligence on 2026-09-11._