grad-ethnography

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

• Third-party content exposure detected (high risk: 0.90). The skill's netnography workflow explicitly directs the agent to identify, lurk in, and analyze online communities (e.g., Discord "台灣獨立遊戲協作站" and Plurk #indiegame), so it ingests untrusted user-generated third-party content that could influence analysis and subsequent actions.