design-pdf
Pass
Audited by Gen Agent Trust Hub on Aug 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a bundled script 'scripts/validate_pdf_bounds.py' to perform automated checks on PDF layout and text positioning. It also references external tools like 'pdffonts' and 'Poppler' for font and rendering inspection.
- [EXTERNAL_DOWNLOADS]: The skill requires the 'pdfplumber' Python package for text extraction. This is a widely-used, legitimate library for PDF analysis.
- [PROMPT_INJECTION]: The skill processes untrusted text from PDF files, creating a potential surface for indirect prompt injection.
- Ingestion points: Text is extracted via the validation script and reviewed by the agent during visual QA steps.
- Boundary markers: The skill does not use specific delimiters or instructions to ignore commands within the extracted PDF text.
- Capability inventory: The skill can read/write files and execute scripts but lacks network access or access to sensitive credentials.
- Sanitization: The validation script truncates extracted text to 120 characters per word, which provides a limited constraint but is not a comprehensive safety filter.
Audit Metadata