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.

CVE-2026-62676 affects Omnigent, an open-source AI agent framework, prior to version 0.3.0. A flawed shell-command parser in omnigent/policies/builtins/_shell.py fails to recognize combined interpreter flags, timeout/nice/setsid/stdbuf wrappers, command substitutions, and background control operators. This allows malicious or prompt-injected commands to bypass policy enforcement, specifically the github.py write_repos and write_branches allowlist and the working_dir.py workspace confinement policies. An authenticated or prompt-injected agent can exploit this to push to unauthorized repositories or branches, or escape the intended workspace sandbox. The vulnerability stems from the parser abstaining (allowing) commands it cannot parse rather than defaulting to deny. The issue has been patched in Omnigent version 0.3.0. Users are advised to upgrade immediately to prevent unauthorized repository access or workspace escape.