content-planner

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

• Third-party content exposure detected (high risk: 0.85). The required workflow runs scripts/wechat_search.js, which fetches Sogou WeChat search result pages at runtime and parses outsider-authored article titles/summaries/source names into JSON that is then used by the agent’s LLM for topic recommendations (indirect prompt injection risk via scraped public web content).