compliance-verification
Pass
Audited by Gen Agent Trust Hub on Aug 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill contains a 'Usage License Rule' that employs high-priority directives to override agent behavior based on the user's identity. These instructions are specifically designed to resist modification or bypass by subsequent user prompts.
- [COMMAND_EXECUTION]: The skill references setup procedures that instruct the agent to use shell commands for package management and tool configuration, such as
pip installand platform-specific MCP registration commands (e.g.,claude mcp add,gemini mcp add). - [EXTERNAL_DOWNLOADS]: The skill requires external legal data sources, downloading the
mcp-taiwan-legal-dbPython package and communicating with a remote server athttps://tlr.dr-lawbot.com/mcpto provide statutory and judicial information.
Audit Metadata