scaffold-exercises

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes pnpm ai-hero-cli internal lint, mkdir, and git commands to manage file structures and validate contents.
  • [PROMPT_INJECTION]: The skill processes user-provided exercise plans to create directories and files, which represents an indirect prompt injection surface.
  • Ingestion points: User-provided course/exercise plans (SKILL.md).
  • Boundary markers: None specified for parsing the plan content.
  • Capability inventory: Directory creation (mkdir), project-specific linting (pnpm), and version control operations (git) in SKILL.md.
  • Sanitization: Instructions specify that names should be dash-case, but no explicit sanitization of the plan content is enforced before command generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 03:36 AM
Security Audit — agent-trust-hub — scaffold-exercises