Scrape

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests content from arbitrary public websites (see SKILL.md and code.md: the full example using target = "https://example.com/products" and the fetch_politely/session.get code that returns response.text), meaning untrusted third-party web content would be read and processed at runtime and could influence subsequent actions.