author-stepwise-skill

Pass

Audited by Gen Agent Trust Hub on Jun 29, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The content is purely instructional and serves as a developer guide for skill scaffolding within a specific framework.
  • [COMMAND_EXECUTION]: The documentation references standard development lifecycle commands such as 'npm run build' and 'npm test', alongside internal testing scripts like 'scripts/lib/tests/skill-generator-references-folder.test.js'. These are intended for the skill developer and do not represent a runtime security threat for an agent.
  • [PROMPT_INJECTION]: Instructions such as 'Read ONLY this file' and constraints on tool usage (Glob, ls, find) are documented as part of a progressive disclosure pattern designed to maintain agent focus and prevent context bloat, rather than attempting to bypass safety filters.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 29, 2026, 03:54 PM
Security Audit — agent-trust-hub — author-stepwise-skill