scaffold-exercises

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute various shell commands to manage the file system and repository state.
  • Evidence: Usage of mkdir -p for directory creation, git mv for renumbering, and pnpm ai-hero-cli internal lint for validation.
  • [INDIRECT_PROMPT_INJECTION]: The skill has a vulnerability surface where it ingests and parses untrusted data ('plans') to determine its actions.
  • Ingestion points: The workflow begins by parsing a user-provided plan to extract section and exercise names (found in SKILL.md).
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded commands within the 'plan' are provided in the skill instructions.
  • Capability inventory: The skill possesses the capability to create directories (mkdir), move files (git mv), and execute package scripts (pnpm) across the workspace.
  • Sanitization: There are no instructions for the agent to sanitize or validate the exercise/section names extracted from the plan before using them in shell commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 06:57 AM
Security Audit — agent-trust-hub — scaffold-exercises