mac-optimize

Pass

Audited by Gen Agent Trust Hub on Mar 4, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses a variety of native macOS command-line tools to gather system performance metrics and hardware information. Evidence: Commands include uname, sysctl, memory_pressure, ps, osascript, lsof, and df to analyze memory, CPU, and running processes.- [COMMAND_EXECUTION]: The skill provides functions to modify system state and terminate processes based on user approval. Evidence: Uses brew services stop, launchctl bootout, defaults write, and pkill to manage background services and applications.- [INDIRECT_PROMPT_INJECTION]: The skill processes output from local system commands, creating a potential surface for indirect prompt injection if process names or service metadata are maliciously crafted.
  • Ingestion points: Command outputs from ps, ls, and osascript.
  • Boundary markers: None explicitly defined for command output processing.
  • Capability inventory: Process termination (kill, pkill), service management (brew, launchctl), and system configuration (defaults).
  • Sanitization: The skill incorporates human-in-the-loop validation by requiring explicit user confirmation before executing any modification or termination commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 4, 2026, 06:38 AM