tao-validate-dataset-format

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

• Third-party content exposure detected (medium risk: 0.65). The runtime workflow runs the tao-daft validate <format> --path ... CLI, which reads the user-supplied dataset files from --path (potentially containing outsider-authored free text like dataset metadata/annotations), and feeds the resulting validation output back into the agent’s LLM context.