Prompting

Pass

Audited by Gen Agent Trust Hub on May 2, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The RenderTemplate.ts utility programmatically identifies template partials using Bun.spawnSync(['ls', ...]). This execution is scoped to the skill's internal directory to facilitate dynamic loading of reusable template components.
  • [EXTERNAL_DOWNLOADS]: Instructions in SKILL.md mandate a status notification using curl to localhost:8888. This local network operation is a common pattern in the author's workflow for providing audio or visual feedback to the user via a local daemon.
  • [SAFE]: The templating engine uses logic-less Handlebars templates and structured YAML data, which is an industry-standard approach for safe and maintainable prompt engineering.
  • [SAFE]: The skill provides extensive documentation on prompt engineering standards and context engineering, aligning with official guidelines from major AI research organizations.
Audit Metadata
Risk Level
SAFE
Analyzed
May 2, 2026, 01:03 AM