chinese-novelist

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill incorporates a local workflow management system known as 'Novel Harness'. This system uses Python scripts such as novel_hook_guard.py and novel_runtime_hook.py alongside hook wrappers in .claude/hooks/. These scripts utilize the subprocess module to execute local validation logic, word count checks, and quality benchmarks. These operations are restricted to the local repository context and serve the intended purpose of novel project management.
  • [SAFE]: The initialization utility scripts/init_novel_harness.py handles the setup of local infrastructure, including template copying and configuration merging for agent hooks. These actions follow standard project setup patterns and do not involve unauthorized network activity or sensitive data access.
  • [SAFE]: The skill uses a structured 'Writing Plan' (02-写作计划.json) and 'Chapter Contracts' to maintain project state and quality standards, demonstrating best practices for complex agent workflows.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 11:41 AM
Security Audit — agent-trust-hub — chinese-novelist