skills/senweaver/senweaver-ide/docx/Gen Agent Trust Hub

docx

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes vendor-provided Python scripts for unpacking and packing Word document structures. Evidence includes calls to scripts/office/unpack.py and scripts/office/pack.py.
  • [EXTERNAL_DOWNLOADS]: The documentation references the well-known docx (docx-js) library for document generation as evidenced by the require('docx') code examples.
  • [PROMPT_INJECTION]: The skill processes untrusted external Word documents via the read_document tool, which is a potential surface for indirect prompt injection. * Ingestion points: The read_document tool parses .docx files. * Boundary markers: None explicitly defined in the documentation. * Capability inventory: Includes file creation, editing, PDF conversion, and XML processing via scripts. * Sanitization: No specific content sanitization is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 08:49 AM