doc-pipeline

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill specifies the installation of well-known and legitimate document processing libraries including python-docx, openpyxl, python-pptx, reportlab, and jinja2 via pip. It also references the author's official GitHub repository for documentation.
  • [PROMPT_INJECTION]: The skill structure indicates a surface for indirect prompt injection. 1. Ingestion points: Document content from PDFs, images, and spreadsheets enters the context via the extraction stages described in SKILL.md. 2. Boundary markers: No explicit boundary markers or delimiters are defined to isolate untrusted document content from the AI's core instructions. 3. Capability inventory: The provided code snippets do not contain subprocess calls, eval/exec, file writes, or network operations; however, the skill defines a workflow where an AI model analyzes text extracted from external sources. 4. Sanitization: The skill does not describe or implement methods to sanitize or validate content extracted from external files before it is processed by the AI.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 03:32 AM