pdf-to-markdown

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security vulnerabilities or malicious patterns were detected. The skill uses industry-standard libraries for PDF processing and follows proper resource management practices.
  • [PROMPT_INJECTION]: The skill processes untrusted PDF files as its primary function, which creates a surface for indirect prompt injection. This is evaluated as safe given the tool's intended use case and specialized function. \n
  • Ingestion points: scripts/extractor.py and scripts/pdf_to_md.py read external PDF files. \n
  • Boundary markers: None. The extracted text is provided as structured Markdown output. \n
  • Capability inventory: The skill's capabilities are restricted to reading PDFs and writing converted Markdown and image files to the filesystem. \n
  • Sanitization: Content is extracted as raw text via standard libraries with no additional filtering for embedded instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 06:22 PM