brave-search-hardened

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

• Third-party content exposure detected (high risk: 0.90). The skill (SKILL.md) and its scripts (search.js and content.js) explicitly perform Brave Search queries and fetch/arbitrarily scrape external webpages (via fetch in search.js and content.js) and then extract and present that page content to the agent, so untrusted public web content can be read and could influence subsequent behavior (indirect prompt injection).