data-engineer

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

• Third-party content exposure detected (high risk: 0.70). The skill includes a runnable script (scripts/run_etl_pipeline.py) whose _extract_api() calls requests.get(url) on a configurable source_config['url'] and loads the returned JSON into the pipeline for subsequent transform/load steps, meaning arbitrary third-party (potentially untrusted) web content would be ingested and could materially influence pipeline behavior.