motherduck-build-data-pipeline

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow (SKILL.md and PIPELINE_IMPLEMENTATION_GUIDE) explicitly instructs the agent to ingest and explore external sources such as "files, cloud storage (S3, GCS, Azure), APIs, databases" (e.g., examples using read_parquet('s3://...') and read_csv('s3://...')), meaning the agent will read untrusted, third-party content that can materially influence pipeline design and subsequent tool actions.