brave-search

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

• Third-party content exposure detected (high risk: 1.00). The skill's search.js and content.js explicitly fetch and parse arbitrary public web pages (search.js -> fetchBraveResults and fetchPageContent calling Brave Search and fetching linked URLs; content.js -> fetch(url) and Readability), so untrusted third-party webpage content is ingested and returned for the agent to read and act on.