setup-repo

Pass

Audited by Gen Agent Trust Hub on Mar 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes git init in the working directory during the repository initialization phase (Step 3).
  • [EXTERNAL_DOWNLOADS]: The skill fetches external agent instructions via the awesome-copilot-search_instructions and awesome-copilot-load_instruction tools to install new capabilities into the project repository (Step 8).
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) during the automated installation of skills.
  • Ingestion points: Untrusted data enters the agent context via the awesome-copilot-load_instruction tool call which fetches external Markdown files.
  • Boundary markers: No boundary markers or "ignore embedded instructions" warnings are used when writing the downloaded content to the .agents/skills/ directory.
  • Capability inventory: The skill possesses significant capabilities including shell command execution (git init) and project-wide file write access (hooks, configuration, and skill files).
  • Sanitization: There is no evidence of sanitization or content validation performed on the external instructions before they are saved and potentially executed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 24, 2026, 02:48 PM