scaffold-exercises
Pass
Audited by Gen Agent Trust Hub on Jul 21, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses standard shell commands including
mkdir,git mv, andgit committo manage file structures and version control. - [COMMAND_EXECUTION]: Executes a local tool via
pnpm ai-hero-cli internal lint. This appears to be a project-specific utility for validating the directory structure and content requirements. - [PROMPT_INJECTION]: The skill processes an 'exercise plan' provided by the user to determine directory names. While this presents a surface for indirect prompt injection or command injection via malicious filenames, the risk is minimal in a standard development environment and the instructions focus on structural formatting.
Audit Metadata