verify-authenticity

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

• Third-party content exposure detected (high risk: 1.00). Step 1 ("联网搜索") requires calling the openclaw search tool with the user's content to retrieve authoritative information from the public web, so the agent fetches and ingests untrusted third-party webpages/search results that are then directly used to influence its verification decisions.