Pass
Audited by Gen Agent Trust Hub on May 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides documentation and instructions for using established PDF manipulation libraries such as pypdf, pdfplumber, and reportlab.
- [PROMPT_INJECTION]: The skill facilitates the processing of external PDF files, which represents an indirect prompt injection surface. Maliciously crafted PDFs could contain instructions intended to influence the agent's behavior during text extraction.
- Ingestion points: External PDF files are opened using
PdfReaderandpdfplumber.openinSKILL.md. - Boundary markers: None identified in the provided instructions.
- Capability inventory: The agent utilizes Python libraries and CLI tools (
pdftotext,qpdf) to read and extract content. - Sanitization: No specific sanitization or filtering of extracted text is described.
Audit Metadata