Omnigent is an open-source AI agent framework and meta-harness for orchestrating coding agents. Prior to 0.3.0, multipart POST /v1/sessions accepts an authenticated user's agent bundle and omnigent/server/bundles.py validate_agent_bundle does not reject a tools..callable dotted Python path. omnigent/runner/tool_dispatch.py _resolve_spec_callable imports the specified module and _execute_spec_callable_tool invokes the resolved function, allowing a bundle to select subprocess.check_output and execute a local command with the runner process permissions. This can expose runner files, environment variables, credentials, workspace data, internal services, and availability without administrator access. This issue is fixed in version 0.3.0.

CVE-2026-62675 affects Omnigent, an open-source AI agent framework for orchestrating coding agents, in versions prior to 0.3.0. The vulnerability exists in the multipart POST /v1/sessions endpoint, where the validate_agent_bundle function in bundles.py fails to reject arbitrary dotted Python paths in the tools callable field. The tool dispatch module resolves and invokes the specified callable, allowing an authenticated user to specify subprocess.check_output or similar dangerous functions. This enables arbitrary local command execution with the permissions of the runner process. Exploitation can expose sensitive data including environment variables, credentials, workspace files, and internal services. The flaw requires only authenticated user access, not administrator privileges, lowering the barrier for exploitation. The issue has been patched in Omnigent version 0.3.0 via input validation on the callable path.