ai-readiness-checklist
Warn
Audited by Snyk on Aug 26, 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). In Phase 1/2/3 this skill reads Metabase entities (tables/transforms/metrics/schemas/collections) via the Metabase MCP server using user-provided names/URIs (e.g.,
read_resource,search), which surfaces outsider-authored free text contained in those entities (like table/field descriptions and saved metric definitions) at runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata