moshu-write
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes local utility scripts using Node.js and Python (e.g.,
check-ai-patterns.js,tracking_commit.py) to perform automated text analysis and maintain project state. These operations are scoped to the project directory and serve the creative writing workflow. - [SAFE]: The skill manages creative assets (outlines, character profiles, and chapters) through a structured file system hierarchy. It uses a robust state-tracking mechanism with atomic file operations to prevent data corruption during long-form project development.
- [SAFE]: No patterns of data exfiltration, prompt injection, or malicious obfuscation were identified. The logic focuses entirely on assisting the user with creative writing tasks and stylistic enforcement.
Audit Metadata