large-document-processing

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a susceptibility to indirect prompt injection as it parses and chunks content from untrusted external document formats.\n
  • Ingestion points: Data enters the agent's context through files such as large_document.pdf and data/bible/nwt_E.epub using parsers like PyMuPDF and ebooklib.\n
  • Boundary markers: Absent. There is no evidence in the provided logic that extracted text chunks are wrapped in delimiters or accompanied by instructions for the AI to ignore embedded commands.\n
  • Capability inventory: The skill possesses the capability to read local files and execute internal setup and extraction scripts (scripts/extract_jwpub.py and scripts/setup_large_document_processing.py).\n
  • Sanitization: Absent. The extraction and chunking code does not include filters or validation routines to detect and neutralize potentially malicious instructional content in the source documents.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 01:10 AM