brave-search

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

• Third-party content exposure detected (high risk: 0.90). This skill directly fetches and parses open web pages (search.js scrapes search results from https://search.brave.com and both search.js and content.js fetch and extract readable content from arbitrary third‑party URLs), so untrusted public web content is ingested and can influence the agent's outputs and actions.