motherduck
Warn
Audited by Snyk on Aug 12, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). SKILL.md describes a MotherDuck/DuckDB workflow where a caller runs SQL via the
md:connection and may ingest data from externally supplied URLs/S3 paths using functions likeread_csv('https://data.example.com/...')andread_parquet('s3://...'), meaning runtime ingestion could include outsider-authored text if the user/attacker supplies or controls those input sources.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata