writing-staffing
Pass
Audited by Gen Agent Trust Hub on May 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a technical reference guide for coordinating creative writing tasks. It outlines a modular architecture where specific roles (writer, outliner, critic) are delegated to separate agent instances to maintain context clarity and voice consistency.
- [EXTERNAL_DOWNLOADS]: The documentation includes citations from well-known academic and research services (ACL Anthology, ArXiv) to provide empirical justification for its multi-agent approach. These references are documented neutrally and point to established technical repositories.
- [COMMAND_EXECUTION]: The resource files contain examples of shell commands for the 'meridian' CLI tool to demonstrate how to spawn agents with specific focus areas and file contexts. These examples are illustrative, using static placeholders rather than dynamically executing untrusted strings.
- [DATA_EXPOSURE]: The skill's design emphasizes the use of 'read-only' agents for simulation and critique tasks, which is a security best practice that limits the ability of those agents to modify or exfiltrate local files.
Audit Metadata