encode-skill

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

• Third-party content exposure detected (high risk: 0.85). The required workflow calls scripts/rest_request.py, which performs a runtime HTTP GET/POST to base_url+path (e.g., https://www.encodeproject.org/...) and then ingests the fetched response body via response.json() / response.text into the returned records/summary (LLM context), so any free-form text contained in that outsider-hosted response can be included.