The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/analyze_codebase.py uses subprocess.run to call the optional mmdc (Mermaid CLI) for rendering SVG images. This execution is handled safely by passing arguments as a list rather than a shell string, which prevents shell injection vulnerabilities. The inputs for diagram generation, such as file paths and module names, are sanitized using a regular expression to ensure they conform to safe Mermaid ID standards.
[DATA_EXFILTRATION]: No network activity or sensitive data access was detected. The tool's scope is limited to scanning a local directory and writing generated diagram files back to a user-specified or default local directory.
[REMOTE_CODE_EXECUTION]: The skill uses static analysis (Python's ast module and regular expressions) to parse imports. It does not execute or import the code it analyzes, avoiding the risks associated with dynamic code execution.

code-to-chart