brave-search

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

• Third-party content exposure detected (high risk: 0.90). The skill performs live web searches against https://search.brave.com and fetches/arbitrary result URLs (see search.js's fetchBraveResults and fetchPageContent, and content.js's URL extraction), ingesting public, untrusted web page content which the agent reads and returns—allowing indirect prompt injection.