skills/liyecom/liye-ai/docx/Gen Agent Trust Hub

docx

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • PROMPT_INJECTION (LOW): Indirect Prompt Injection risk via document processing.
  • Ingestion points: The skill ingests untrusted Word documents via the docx processing logic.
  • Boundary markers: Missing explicit boundary markers or instructions to ignore commands within documents.
  • Capability inventory: Includes file read/write and content extraction via python-docx.
  • Sanitization: No explicit sanitization or filtering of extracted content before processing.
  • COMMAND_EXECUTION (SAFE): The verification step references a local linting script (node .claude/scripts/sfc_lint.mjs). This is a standard internal verification mechanism and does not present an external threat surface.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:47 PM