prompt

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a robust safety control by requiring explicit user confirmation (typing 'continue') before any files are written to the disk.
  • [COMMAND_EXECUTION]: Employs standard Unix utilities (ls, mkdir, sort, tail) to manage the ./prompts/ directory and ensure proper file numbering. These operations are scoped to a specific local path and do not involve privilege escalation or network access.
  • [DATA_EXPOSURE]: The skill is designed to read and write within the local project structure (specifically ./prompts/) and references existing project files using the @file syntax to provide context, which is standard behavior for development-focused agents.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 04:10 AM
Security Audit — agent-trust-hub — prompt