motherduck-load-data

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflow and reference doc (references/INGESTION_PATTERNS.md and SKILL.md) explicitly instruct reading remote public/third-party sources (s3://, https://, public buckets, read_parquet/read_csv/read_json/delta_scan, etc.), so the agent will fetch and interpret untrusted user-controlled content as part of its ingestion workflow which can materially influence subsequent SQL/tool actions.