tw-stu-ai-literacy

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

• Third-party content exposure detected (high risk: 0.80). The skill's required Step 5 ("查來源：...用 WebSearch 查證") instructs using WebSearch to verify AI outputs (and the降級方案 references WebSearch availability), which clearly requires fetching and reading open/public third-party web content that could influence subsequent judgments or actions.