mac-optimize

Pass

Audited by Gen Agent Trust Hub on Oct 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes shell commands to gather system metadata and apply optimization settings.
  • Evidence: Use of ps, sysctl, lsof, osascript, brew, launchctl, and defaults commands in SKILL.md to analyze and modify system state.
  • Specifically, it modifies user-level configuration via defaults write com.apple.dock and manages services using launchctl bootout.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes output from system utilities which could contain untrusted data that might influence the agent's behavior.
  • Ingestion points: Reads and parses output from ps (process names), lsof (service names), and the local resources/optimization-guide.md file.
  • Boundary markers: No specific delimiters or "ignore instructions" markers are used when the agent processes the output of the diagnostic commands.
  • Capability inventory: The skill has the capability to terminate processes (pkill), stop services (brew services stop), and modify system settings (defaults).
  • Sanitization: There is no evidence of sanitization or filtering applied to the process names or service descriptions before they are interpreted by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 28, 2026, 04:33 PM