scaffold-exercises

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes shell commands like mkdir -p to create nested directory structures and git mv to rename or move exercise folders while preserving git history. It also calls pnpm ai-hero-cli internal lint to validate the created structure. These actions are within the expected scope of a scaffolding tool.
  • [INDIRECT_PROMPT_INJECTION]: The skill takes user-supplied exercise plans to generate file system paths and basic Markdown content. \n
  • Ingestion points: User-provided exercise plans or section names (referenced in the workflow section of SKILL.md). \n
  • Boundary markers: None identified. \n
  • Capability inventory: Local file system access (mkdir, git mv) and command execution (pnpm). \n
  • Sanitization: There is no mention of sanitizing or validating the input strings before they are used in shell commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 01:25 AM
Security Audit — agent-trust-hub — scaffold-exercises