book-writing-workspace

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes several Python scripts (setup_workspace.py, count_chars.py, convert_md_to_review.py) to automate workspace setup and manuscript processing. Technical review of the source code shows these scripts use standard library modules to perform safe file system operations and regex-based text transformations within the project directory.
  • [EXTERNAL_DOWNLOADS]: Documentation within the converter agent instructions suggests the use of the vvakame/review Docker image for PDF generation. This is a recognized tool for Re:VIEW-based publishing and is documented neutrally as a recommended environment for the build process.
  • [COMMAND_EXECUTION]: The provided Git prompts (gc_Commit.prompt.md, gcp_Commit_Push.prompt.md, etc.) define clear steps for the AI to perform version control tasks. These operations are limited to standard Git commands and include validation steps to prevent errors.
  • [SAFE]: No instances of prompt injection, data exfiltration, obfuscation, or persistence mechanisms were found. The skill follows best practices for secret management by instructing users to use environment variables or local configurations where necessary.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 07:29 AM