brave-search-api

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

• Third-party content exposure detected (high risk: 1.00). This skill directly queries the public Brave Search API (e.g., GET https://api.search.brave.com/res/v1/web/search) and instructs extracting/reading titles, URLs, and descriptions from web search results in SKILL.md, which are untrusted third-party web contents that could influence agent decisions and enable indirect prompt injection.