skills/terrylica/cc-skills/uninstall/Gen Agent Trust Hub

uninstall

Pass

Audited by Gen Agent Trust Hub on Jun 26, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute pkill, rm -rf, and defaults delete. These commands are used to terminate the application, remove the app bundle from /Applications/, and clear user preferences. These are standard operations for an uninstaller, and the skill includes an AskUserQuestion prompt to obtain user consent before proceeding.
  • [PROMPT_INJECTION]: The 'Self-Evolving Skill' section contains instructions for the AI to 'fix this file immediately' if it discovers new paths that should be cleaned up. This is an instruction to the agent to modify its own logic based on runtime observations, which could potentially lead to unintended modifications of the skill's behavior over time.
  • [DATA_EXPOSURE]: The skill targets specific preference domains (com.terryli.floating-clock) and application paths. There is no evidence of unauthorized data access or external exfiltration.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 26, 2026, 12:25 AM
Security Audit — agent-trust-hub — uninstall