brave-search

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md explicitly instructs the agent to call the Brave Search API (GET https://api.search.brave.com/res/v1/web/search) and consume web search results, snippets, and URLs from arbitrary public websites, which are untrusted third‑party content that the agent is expected to read and could materially influence its next actions.