NYC

publication-converter

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE] (SAFE): The skill documentation and structure indicate a benign purpose of document conversion. It follows standard architectural patterns for file processing.
  • [Indirect Prompt Injection] (LOW): The skill processes untrusted user-provided markdown content, which represents an attack surface for indirect prompt injection.
  • Ingestion points: Raw markdown text from chat or external markdown files via markdown_processor.py.
  • Boundary markers: Not explicitly defined in the provided documentation, but standard markdown parsing is used.
  • Capability inventory: File system write access for EPUB generation (epub_generator.py).
  • Sanitization: The documentation explicitly states that HTML characters (e.g., <, >, &) are safely escaped during conversion to XHTML, mitigating cross-site scripting risks within the e-reader environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:58 PM