weibo

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

• Third-party content exposure detected (high risk: 0.80). This skill requests and parses real-time user-generated hot-search data from Weibo's public endpoint (https://weibo.com/ajax/side/hotSearch) and directly reads/outputs those topic strings, exposing the agent to untrusted third-party content that could carry indirect prompt injection.