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
Risk Level
SAFE
Analyzed
Aug 1, 2026, 11:05 AM
Security Audit — agent-trust-hub — scaffold-exercises