looker-architect
Warn
Audited by Snyk on Jul 29, 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). The runtime workflow ingests outsider-authored free text when it executes the “Self-Healing SQL Loop” by extracting dashboard tiles (from the repository) and then calling Looker MCP tools
run_dashboard/queryto execute the generated SQL, where the tile configuration and any text fields originate from user-provided/outsider-authored LookML content (including dashboards exported or edited from non-trusted sources).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata