dev-browser

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly automates browsing and scraping of arbitrary public websites and APIs—e.g., SKILL.md and examples use page.goto to visit URLs, references/scraping.md shows capturing/replaying network responses from public endpoints (e.g., "UserTweets" and /api/data), and src/client.ts/getAISnapshot reads page DOM content—so the agent will fetch and interpret untrusted, user-generated third‑party content.