women-ai-topic-radar

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

• Third-party content exposure detected (high risk: 1.00). The skill's workflow (see "Gather Social Signals First" in SKILL.md and references/source-playbook.md) explicitly requires fetching and reading user-generated content from public platforms (Xiaohongshu, Weibo, WeChat official accounts, X/Twitter) via sensight or manual browsing, which the agent must interpret and use to filter, score, and decide next actions.