document-processing

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (LOW): The skill defines procedures for extracting text and data from external office documents (PDF, Word, Excel), which represents an attack surface for indirect prompt injection.
  • Ingestion points: The skill focuses on processing external files like .pdf, .xlsx, .docx, and .pptx.
  • Boundary markers: There are no instructions provided for using delimiters or warnings to ignore embedded instructions within processed documents.
  • Capability inventory: The guide describes capabilities for file reading, text extraction, and metadata manipulation using libraries such as pypdf, openpyxl, and python-docx.
  • Sanitization: No mention of sanitization, escaping, or validation of content extracted from these external documents.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:17 PM