brave-search

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

• Third-party content exposure detected (high risk: 0.90). The skill clearly fetches and parses open web content (search.js calls https://search.brave.com and its fetchPageContent function fetches external result links, and content.js fetches arbitrary URLs) and returns extracted page content that the agent is expected to read/interpret as part of its workflow, creating a pathway for untrusted third-party content to influence actions.