scaffold-exercises

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses mkdir, git mv, git commit, and pnpm ai-hero-cli internal lint to manage project files and folders. These are standard commands for development workflows.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes an external plan to generate file structures, creating a surface for injection. 1. Ingestion points: The 'plan' parsed at the beginning of the workflow. 2. Boundary markers: None. 3. Capability inventory: File system creation, file writing, and execution of git/pnpm tools. 4. Sanitization: The instructions include strict formatting rules for names (dash-case, lowercase), which limits the potential for unexpected output from malicious plan inputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 02:34 PM