fetch

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches arbitrary open-web URLs via the required "url" parameter (see SKILL.md and REFERENCE.md POST https://api.browserbase.com/v1/fetch) and EXAMPLES.md shows the agent parsing response.content (HTML/JSON) and acting on extracted data (titles, JSON), so it ingests untrusted third-party content that could contain instructions influencing subsequent actions.