docx

Warn

Audited by Snyk on Feb 16, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). The skill expressly reads and processes arbitrary Word documents provided by users (e.g., "示例 3: 把这些 Word 文档的内容提取出来" and "使用 docx 读取文档"), which are untrusted user-generated files that the agent will parse and interpret, enabling indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:25 PM