agent-cli-creator

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes shell commands to manage the development lifecycle, including checking the status of the local kimi-webbridge daemon, initializing Go modules, installing the cobra library, and building/testing the generated CLI tool.
  • [EXTERNAL_DOWNLOADS]: References to external resources (Kimi/Moonshot AI's official website and common Go libraries on GitHub) are for legitimate documentation and package management purposes.
  • [PROMPT_INJECTION]: The 'Site Archaeology' protocol involves the agent ingesting data from external websites (accessibility trees and network responses). This constitutes an indirect prompt injection surface; however, the skill provides a rigorous, step-by-step methodology to structure this data collection, which is fundamental to the skill's purpose of web automation.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 02:53 AM
Security Audit — agent-trust-hub — agent-cli-creator