moai-platform-database-cloud

Pass

Audited by Gen Agent Trust Hub on Mar 30, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill acts as a technical reference and execution environment for cloud database management. It correctly promotes security best practices, such as using Row-Level Security (RLS) and protecting sensitive service role keys.\n- [INDIRECT_PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection by design, as it utilizes tools to ingest external documentation.\n
  • Ingestion points: Documentation is fetched at runtime using mcp__context7__get-library-docs.\n
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to treat external documentation as untrusted data.\n
  • Capability inventory: The skill provides access to several database CLIs (psql, neonctl, firebase, supabase) and file system operations (Write).\n
  • Sanitization: There is no evidence of sanitization for content retrieved from external documentation libraries.\n- [EXTERNAL_DOWNLOADS]: The skill references standard, well-known libraries and SDKs for the supported platforms (e.g., @supabase/supabase-js, @neondatabase/serverless, firebase). These are recognized as trusted industry-standard dependencies.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 30, 2026, 11:34 PM