ziniao-account

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill makes extensive use of ziniao-cli, which is the intended interface for this tool. It executes commands such as account list, account create, and account auth-add. These are standard administrative operations within the context of the platform.
  • [DATA_EXPOSURE]: The skill provides instructions for managing account and employee data, including clear warnings about data management differences between 'Boss' and 'Staff' accounts. It handles administrative metadata rather than sensitive system files or credentials.
  • [REMOTE_CODE_EXECUTION]: There are no patterns of remote code execution. All actions are performed locally via the ziniao-cli binary or directed to specified internal API endpoints (/superbrowser/rest/v1/...).
  • [PROMPT_INJECTION]: The skill uses phrases like 'CRITICAL' to emphasize important operational steps and documentation requirements, which is benign instructional language in this context.
  • [SAFE]: The skill follows best practices for command-line tool usage, such as suggesting --yes flags for high-risk operations (deletion) and providing guidance for environment-specific issues like path conversion in Windows Git Bash.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 03:40 PM
Security Audit — agent-trust-hub — ziniao-account