Pass
Audited by Gen Agent Trust Hub on Jun 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses established Python libraries for PDF processing, including pypdf, pdfplumber, pandas, reportlab, and pytesseract. These are standard tools for text extraction, merging, splitting, and OCR.
- [SAFE]: The command-line tools mentioned (pdftotext, qpdf, pdftk) are industry-standard utilities for PDF management. The commands provided follow best practices for their respective tasks.
- [SAFE]: The instructional text, including the warning about Unicode subscripts in ReportLab, is benign and provides legitimate technical guidance for formatting.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from PDF files, which represents an indirect prompt injection surface.
- Ingestion points: Reads content and metadata from user-provided PDF files via pypdf, pdfplumber, and pytesseract (SKILL.md).
- Boundary markers: None identified; extracted text is processed directly.
- Capability inventory: File system write access for saving processed PDFs/Excel files and shell command execution via PDF CLI tools (SKILL.md).
- Sanitization: No explicit sanitization or filtering of extracted text is described before processing or interpolation into prompts.
Audit Metadata