claude-md-improver

Pass

Audited by Gen Agent Trust Hub on May 7, 2026

Risk Level: SAFE
Full Analysis
  • File Access Patterns: The skill searches for and reads configuration files within the project repository and the user's home directory. This behavior is consistent with its primary purpose of evaluating project-specific and global AI context files.
  • Controlled File Modification: The skill includes instructions to present a comprehensive quality report and obtain explicit user confirmation before applying any edits to files. This human-in-the-loop requirement provides oversight for the modification process.
  • Discovery Operations: Uses a standard shell command to find documentation files. The command is scoped to the current directory and specific filenames, representing a low-risk approach to file discovery.
Audit Metadata
Risk Level
SAFE
Analyzed
May 7, 2026, 05:20 PM