The Agent Skills Directory

[SAFE]: The skill operates entirely locally, using standard Unix utilities such as grep, sed, awk, and find to parse Drupal project files. It does not perform any network operations, and no evidence of data exfiltration or credential harvesting was found.
[SAFE]: The scripts are written in plain Bash and are transparent in their operation. They include basic sanitization (e.g., JSON escaping) when generating schema files to prevent structural data from being misinterpreted as control characters.
[SAFE]: No obfuscation, prompt injection, or persistence mechanisms were detected. The skill's execution is limited to generating documentation within the project's own directory structure.

structural-index