scaffold-exercises
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses standard filesystem and version control commands (mkdir, git) and a local utility (pnpm ai-hero-cli) to automate the scaffolding of exercise directories.
- [PROMPT_INJECTION]: The skill accepts user-provided plans to generate directory names and file stubs, which is a surface for indirect prompt injection.
- Ingestion points: Parsing of the user-provided plan in SKILL.md.
- Boundary markers (absent): No specific delimiters are defined to isolate the input plan from instructions.
- Capability inventory: Directory creation, file writing, and git operations across the workflow in SKILL.md.
- Sanitization (absent): No explicit sanitization of plan-derived strings is performed before their use in shell commands.
Audit Metadata