scaffold-exercises
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill guides the agent to perform local file system operations using
mkdir -p,git mv, and a development toolpnpm ai-hero-cli internal lint. These actions are restricted to theexercises/directory and align with the skill's purpose of scaffolding course content.- [PROMPT_INJECTION]: The skill processes user-provided course plans to determine the directory structure, which constitutes a surface for indirect prompt injection. Ingestion points: User-provided exercise plans (SKILL.md). Boundary markers: Not present. Capability inventory: File system manipulation (mkdir,git mv), file writing, and execution of local linting tools (SKILL.md). Sanitization: Not present; the skill relies on the agent's interpretation of the plan.
Audit Metadata