ocrmypdf-api

Pass

Audited by Gen Agent Trust Hub on Apr 6, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill documents how to process external PDF files which represents an indirect prompt injection surface.
  • Ingestion points: The Flask integration example in SKILL.md accepts files via POST requests (request.files['file']).
  • Boundary markers: The examples do not include boundary markers or instructions for the agent to ignore embedded commands within the processed PDFs.
  • Capability inventory: The skill utilizes ocrmypdf.ocr to process files and os.unlink for file management.
  • Sanitization: The provided code snippets do not implement sanitization or validation of the input PDF content before processing.
  • [SAFE]: The skill provides standard documentation for the OCRmyPDF library. Package installations and file handling patterns in the examples are appropriate for the described functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 6, 2026, 10:50 AM