refactor

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill may download and execute the @command-center/command-center package using npx if the application is not already installed. This is a legitimate vendor resource provided by the author to run the backend service.
  • [COMMAND_EXECUTION]: Local shell commands are used to manage the lifecycle of the backend service (node, npx) and to interact with the repository's git state (git diff, git rev-parse).
  • [CREDENTIALS_UNSAFE]: The skill reads an authentication token from the vendor's local configuration directory (~/.commandcenter/global/session-token.json) to authenticate requests to the backend. This is standard session management for the tool.
  • [REMOTE_CODE_EXECUTION]: The skill initiates refactoring workflows where code modifications are generated by the backend and applied to the local working tree by local agents. This behavior is consistent with the skill's documented purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 12:10 AM
Security Audit — agent-trust-hub — refactor