macos-uninstall
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill involves the use of high-impact commands such as
rm -rfandbrew uninstallto delete directories. These operations are necessary for uninstallation but carry an inherent risk of data loss if the target paths are incorrect. - [INDIRECT_PROMPT_INJECTION]: The skill takes user input for application names and bundle IDs which are then used in shell commands. 1. Ingestion points: $APP and $BID variables in SKILL.md. 2. Boundary markers: The skill instructs the agent to perform an inventory before removal to verify paths. 3. Capability inventory: Includes commands like
rm,brew,ls, andtar. 4. Sanitization: No automated sanitization is present; the skill relies on manual verification.
Audit Metadata