autoviz

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

• Third-party content exposure detected (high risk: 0.80). The skill ingests and analyzes arbitrary user/third-party data (e.g., pd.read_csv on provided file paths and the Streamlit file_uploader which accepts uploaded CSVs) and then reads/interprets that content as part of its workflow, exposing the agent to untrusted, user-generated input.