scaffold-exercises

Pass

Audited by Gen Agent Trust Hub on Aug 13, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses standard shell commands to manage the file system and version control.
  • Evidence: Executes mkdir -p to create nested directory structures.
  • Evidence: Uses git commit and git mv to manage changes and renames within the repository.
  • Evidence: Runs pnpm ai-hero-cli internal lint to verify that created files meet project standards.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes a user-provided 'plan' to determine directory and file names.
  • Ingestion points: Step 1 of the workflow extracts metadata from a plan in the conversation context.
  • Boundary markers: Absent; however, the skill's instructions scope operations to the exercises/ directory.
  • Capability inventory: Direct file system writes, git operations, and local CLI execution.
  • Sanitization: Absent; the skill relies on the subsequent linting step to identify structural issues.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 13, 2026, 03:09 AM
Security Audit — agent-trust-hub — scaffold-exercises