pdf-to-docx

Pass

Audited by Gen Agent Trust Hub on Jul 8, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted PDF files, which represents an attack surface for indirect prompt injection where malicious instructions embedded in a document could influence agent behavior.
  • Ingestion points: PDF files are processed as input for conversion in various examples throughout SKILL.md.
  • Boundary markers: The skill does not provide specific instructions or delimiters to the agent to treat document content as untrusted data or to ignore embedded instructions.
  • Capability inventory: The skill utilizes capabilities for file system writes through the cv.convert, new_doc.save, and json.dump methods mentioned in SKILL.md.
  • Sanitization: There is no evidence of sanitization, filtering, or validation of the text extracted from the PDF files before it is processed or written to the output Word documents.
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions for installing the pdf2docx and Pillow libraries and references official documentation and source code repositories.
  • Evidence: Instructions include 'pip install pdf2docx' and links to the official GitHub repository and PyPI package for the library.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 8, 2026, 07:46 PM
Security Audit — agent-trust-hub — pdf-to-docx