Browser Abstraction Layer

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

• Third-party content exposure detected (high risk: 0.90). This skill's scrape_url and scrape_with_fallback logic (and usage examples like "Browse to https://example.com/article") explicitly fetches and analyzes arbitrary public web pages and social media content (patterns listed for threads.net, instagram.com, twitter.com/x.com), meaning the agent will consume untrusted third-party/user-generated content that could carry indirect prompt injections.