scaffold-exercises
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes "pnpm ai-hero-cli internal lint", which is a project-specific command used to validate the generated exercise structure.
- [COMMAND_EXECUTION]: The skill uses shell commands like "mkdir -p" and "git mv" to create and organize directories and files based on instructions.
- [INDIRECT_PROMPT_INJECTION]: The skill processes a user-provided plan to generate directory and file names, creating an indirect injection surface.
- Ingestion points: User-supplied exercise plan (Workflow step 1).
- Boundary markers: None present in the instructions to delimit user data.
- Capability inventory: Uses "mkdir", "git mv", and "git commit" to modify the filesystem and repository.
- Sanitization: No specific sanitization or validation of the plan content is described before using names in shell commands.
Audit Metadata