pdf-image-text-extractor
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary logic in
scripts/pdf_text_extractor.pyperforms text extraction using thePyMuPDFlibrary locally. It includes proper validation to ensure the provided file path exists and has a.pdfextension before processing. - [SAFE]: No network activity was detected in the script. The README and SKILL.md emphasize a 'local-only' execution model, and the code confirms this by not importing any network-related libraries like
requests,urllib, orsocket. - [SAFE]: Dependency management is standard, specifying
pymupdf>=1.23.0which is a well-known and trusted library for PDF manipulation. - [COMMAND_EXECUTION]: The skill instructions prompt the agent to execute the Python script via
python scripts/pdf_text_extractor.py <pdf_file_path>. While this involves shell execution, the parameters are restricted to local file paths and the script itself is bundled with the skill, presenting no immediate risk of injection or unauthorized access beyond the intended scope.
Audit Metadata