builtwith

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime workflow calls BuiltWith public API endpoints (e.g., https://api.builtwith.com/v21/api.json, lists2, trends, etc.) using user-supplied parameters like LOOKUP/TECH, and the LLM would ingest the API’s response body text, which is outsider-authored data from a third-party web service.