NYC

business-document-generator

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill processes user-provided data via JSON files to generate PDF documents.
  • Ingestion points: The scripts/generate_document.py script reads data from a JSON file which may contain untrusted user input.
  • Boundary markers: Absent; user data is directly mapped to document fields.
  • Capability inventory: The skill is capable of writing PDF files to the local file system using pypdf and reportlab.
  • Sanitization: No sanitization is performed on the input strings before they are embedded into the generated PDF files.
  • [Unverifiable Dependencies] (SAFE): The skill relies on standard, well-known Python packages (pypdf, reportlab) for PDF generation, which is a routine and expected behavior for this use case.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:07 PM