The Agent Skills Directory

[SAFE]: The skill uses established libraries (ReportLab, PyMuPDF, Typer) for PDF generation and follows standard CLI patterns. No malicious code, obfuscation, or unauthorized network operations were detected.- [PROMPT_INJECTION]: The skill ingests untrusted data (columns, rows, titles) via CLI arguments or JSON files to generate PDF documents. This represents an indirect prompt injection surface where malicious content in processed data could influence downstream systems that parse the resulting PDFs. (Ingestion points: generate.py CLI and spec file; Boundary markers: Absent; Capability inventory: File writing in generate.py; Sanitization: Absent).- [COMMAND_EXECUTION]: The skill employs uv run and shell scripts for execution and environment setup, which are appropriate for its stated purpose of document generation.

create-table