bellingcat-websites

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

• Third-party content exposure detected (high risk: 0.75). The required workflow is to use multiple public web investigation tools (e.g., Wayback Machine, urlscan.io, Shodan, PublicWWW) that fetch and return third-party web page/content text at runtime, which can include outsider-authored free text that the agent may ingest into the LLM context.