tw-edu-learning-portfolio
Warn
Audited by Snyk on May 4, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). Flagged because SKILL.md explicitly enables an automatic WebSearch connector ("WebSearch(自動啟用)" and under MCP 整合更新: "WebSearch(已啟用):搜尋最新課綱資料、教學素材、時事情境"), meaning the agent will fetch and read open/public web content that can influence its outputs and actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata