goal-mode

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes a local bash script, scripts/goal-notify.sh, to display macOS notifications. This script invokes osascript, a standard macOS utility for executing AppleScript, which is a common practice for desktop integration.
  • [COMMAND_EXECUTION]: The notification script accepts user-provided input (the task condition and status updates) and interpolates it into AppleScript commands. To prevent injection attacks, the script implements an esc function that correctly escapes double quotes (s/"/\\"/g), ensuring the payload remains within the intended AppleScript string literal.
  • [SAFE]: The skill's behavior aligns perfectly with its stated purpose of wrapping the native /goal command with periodic progress updates. No remote code execution, external downloads, data exfiltration, or persistence mechanisms were detected.
  • [SAFE]: The allowed-tools list is restricted to standard file and shell operations necessary for the skill's function, and no suspicious metadata or obfuscated content is present.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 05:44 AM
Security Audit — agent-trust-hub — goal-mode