weibo-hot-search
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill uses agent.browser.execute_task to visit and scrape public Weibo pages (https://weibo.com) to extract hot-search items, which are user-generated/untrusted third-party contents that the agent will read and interpret.
Audit Metadata