The Agent Skills Directory

[SAFE]: The skill implements logic for validating domain-specific data (e.g., CSI codes, task dependencies, and BIM GUIDs) using standard Python libraries. No suspicious command execution or network exfiltration patterns were identified.
[SAFE]: All metadata and URLs are consistent with the vendor's domain (datadrivenconstruction.io).
[SAFE]: The requested filesystem permissions are appropriate for a skill designed to process and validate project data files such as CSV, Excel, and JSON.
[INDIRECT_PROMPT_INJECTION]: While the skill ingests external data files (estimates, BIM exports), it performs specific field-level validation and range checks which serve as a form of input sanitization. The risk is minimal and consistent with the intended use case.

input-validation