streamlit

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests untrusted third-party content — e.g., user-uploaded files via st.file_uploader (Data Explorer / load_uploaded_file) and an example fetch_api_data(endpoint) that performs requests.get(endpoint) — and then reads/displays/analyzes that content as part of the app workflow, which could enable indirect prompt injection.