The Agent Skills Directory

[SAFE] (SAFE): No malicious patterns, obfuscation, or sensitive data access were detected. The content is limited to instructional markdown.
[NO_CODE] (INFO): The skill consists of a single markdown file with no scripts or code execution capabilities. It relies on external reference files not included in this analysis.
[PROMPT_INJECTION] (INFO): The skill is designed to process untrusted document data (PDFs, invoices). While the skill instructions are benign, implementing agents should use sanitization to prevent data-driven injection at runtime.

document-ai