doc-pipeline

Pass

Audited by Gen Agent Trust Hub on Jul 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a document processing workflow using well-known and standard Python libraries (python-docx, openpyxl, python-pptx, reportlab, jinja2).
  • [SAFE]: External links point to the official GitHub repository of the skill's author (claude-office-skills), which is consistent with the skill's metadata and represents normal vendor functionality.
  • [PROMPT_INJECTION]: The skill is designed to ingest and process data from external files (e.g., PDF, Excel, Images). Evidence: 1. Ingestion points: Document input variables ($input_file). 2. Boundary markers: Absent in implementation snippets. 3. Capability inventory: Document extraction, transformation, and AI-based analysis. 4. Sanitization: Not specified in the template. While this creates a potential surface for indirect prompt injection from malicious document content, this is an inherent property of the intended functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 8, 2026, 07:46 PM
Security Audit — agent-trust-hub — doc-pipeline