rc-scaffold-exercises

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to manage the filesystem and run project-specific tools.
  • Evidence: The workflow includes using mkdir -p for directory creation, git mv for renaming, and pnpm ai-hero-cli internal lint for validation.
  • [PROMPT_INJECTION]: The skill processes untrusted user data (a "plan") to drive its automated actions, creating an indirect prompt injection surface.
  • Ingestion points: The skill parses a user-provided plan in Step 1 of the workflow to extract section and exercise names (found in SKILL.md).
  • Boundary markers: The instructions do not specify delimiters or markers to separate the user's plan from the agent's internal instructions.
  • Capability inventory: The agent has access to filesystem modification (mkdir), version control (git), and package manager execution (pnpm).
  • Sanitization: There are no instructions to sanitize or validate the content of the plan before using it to generate shell arguments for directory names or readme content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 04:57 AM
Security Audit — agent-trust-hub — rc-scaffold-exercises