PDF Generator

Pass

Audited by Gen Agent Trust Hub on Jun 3, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized data access were detected. The skill functions purely as a documentation resource providing reference code for PDF generation.
  • [PROMPT_INJECTION]: The skill contains Python code snippets (found in templates.md and advanced.md) that use f-strings and string interpolation to build HTML templates. This identifies a surface for indirect prompt injection if an agent uses these patterns to process untrusted external data.
  • Ingestion points: Functions such as generate_invoice, generate_resume, and batch_generate accept data objects that are directly interpolated into HTML structures.
  • Boundary markers: No specific delimiters or instructions are provided in the documentation to warn the agent about untrusted data input.
  • Capability inventory: The snippets use standard file-writing capabilities (weasyprint.write_pdf, pypdf.PdfWriter.write) necessary for PDF creation.
  • Sanitization: The provided examples do not include HTML escaping or sanitization of the interpolated data variables.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 3, 2026, 02:38 AM
Security Audit — agent-trust-hub — PDF Generator