search

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly queries the open web via the Browserbase Search API (POST https://api.browserbase.com/v1/search) and the docs (SKILL.md and EXAMPLES.md) show chaining search results to a /fetch call to retrieve and process arbitrary public page content, so the agent will read untrusted third‑party content that can influence subsequent actions.