agent-creator
Pass
Audited by Gen Agent Trust Hub on Jul 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill functions as a template generator for agent configuration files. It incorporates security best practices by guiding the user to define explicit boundaries, mission statements, and 'not allowed' actions for created subagents to prevent role-bleeding and unauthorized behavior.
- [SAFE]: The skill includes technical guidance on TOML structure (e.g., field ordering) to prevent silent configuration failures where security instructions might be ignored by the runtime engine due to syntax technicalities.
- [SAFE]: The skill manages external capabilities (MCP servers and skills) through instructional guidance rather than automated installation, requiring explicit user approval before including preferred skills in configurations.
- [SAFE]: The provided validation scripts (using
grep) are used solely for local file integrity checks to ensure the generated TOML adheres to supported schemas and does not contain unauthorized fields.
Audit Metadata