rc-setup-context-repo

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements documentation scaffolding and synchronization within the local workspace. All operations (file reads, folder creation, and script execution) are scoped to the project environment.
  • [COMMAND_EXECUTION]: The skill generates and provides a Python script (sync_workspace_instructions.py) designed to copy markdown files between project directories. This is a standard project management task and does not involve arbitrary command execution or untrusted input.
  • [DATA_EXFILTRATION]: No network operations or external data transmissions are performed. The skill only interacts with local project files to generate documentation like ARCHITECTURE.md and CONTEXT.md.
  • [PROMPT_INJECTION]: The instructions follow a strict 'ask one question at a time' and 'confirm with user' flow, preventing the model from acting autonomously or bypassing instructions.
  • [EXTERNAL_DOWNLOADS]: There are no external dependencies or remote script downloads detected. The project relies on standard library Python functionality for its sync script.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 04:56 AM
Security Audit — agent-trust-hub — rc-setup-context-repo