trae-agent-writer
Pass
Audited by Gen Agent Trust Hub on Mar 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill acts as a template generator and instructional framework for documentation and agent definition. It does not execute arbitrary code, perform network operations, or handle sensitive credentials.\n- [SAFE]: The instructions include robust security guidelines, such as the mandatory inclusion of a 'What This Agent Should NOT Do' section in generated agent definitions. This effectively creates safety boundaries and negative constraints for sub-agents.\n- [SAFE]: The skill enforces a 'Path Rule' that requires relative paths and placeholder parameters, preventing risks associated with absolute path traversal or exposure of the host system's file structure.
Audit Metadata