complexa-sweep

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

• Third-party content exposure detected (low risk: 0.10). The required runtime workflow ingests outsider-authored free text only insofar as it is written into a user-supplied sweeper YAML under configs/sweeps/ and then parsed by script_utils/generate_inference_configs.py to generate Hydra inference/eval config files; it does not read arbitrary external feeds/web pages or third-party text sources.