macos
Warn
Audited by Gen Agent Trust Hub on Mar 7, 2026
Risk Level: MEDIUMCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates arbitrary command execution using the Python
subprocessmodule to perform file operations, query system information, and monitor resources. - [COMMAND_EXECUTION]: Includes instructions for privilege escalation by recommending the use of
sudoto bypass system permission errors during command execution. - [COMMAND_EXECUTION]: Enables system persistence mechanisms through the use of
launchctlto load and manage background daemons and services via plist files. - [COMMAND_EXECUTION]: Utilizes
osascriptto execute AppleScript, allowing the agent to interact with the macOS GUI and control installed applications. - [COMMAND_EXECUTION]: The skill presents an attack surface for indirect prompt injection by dynamically constructing shell commands from user-provided JSON payloads and queries without explicit sanitization logic or defined boundary markers.
Audit Metadata