datahub-sql-workflow
Warn
Audited by Snyk on Aug 11, 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 requires calling
find_sql_context(question=<user's complete question>), so the outsider-authored free text (the user question) is directly ingested by the workflow at runtime before any evidence selection or grounding.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata