writing-plans-plus

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides a structured methodology for task management and verification that does not introduce security risks.
  • [PROMPT_INJECTION]: The instructions are operational and focus on plan formatting; they do not contain any commands to bypass safety protocols or override system instructions.
  • [DATA_EXFILTRATION]: No unauthorized network operations or sensitive file access patterns were found. The skill includes a best-practice example specifically warning against the inclusion of real secrets in environment files.
  • [EXTERNAL_DOWNLOADS]: The skill's examples reference well-known and trusted Node.js packages for the Supabase service, which is a common and legitimate development practice.
  • [COMMAND_EXECUTION]: While the skill defines tasks that involve code changes and installation steps, it does not facilitate arbitrary or dangerous shell command execution within its own logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 03:39 AM