relational-database-mcp-cloudbase

Pass

Audited by Gen Agent Trust Hub on Jul 7, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill contains references to sibling documentation and configuration files located on the official vendor repository at cnb.cool. These references are used to coordinate between integrated skills.
  • [COMMAND_EXECUTION]: The skill defines tools for executing SQL statements and managing database lifecycles through MCP. It incorporates safety procedures, such as requiring explicit confirmation for destructive actions like instance deletion and recommending read-only verification before data mutations.
  • [PROMPT_INJECTION]: The skill describes an interface for ingesting external data, which creates a potential surface for indirect prompt injection.
  • Ingestion points: Data returned from SQL queries via the querySqlDatabase tool.
  • Boundary markers: The instructions do not define specific delimiters or guidelines to distinguish retrieved data from agent instructions.
  • Capability inventory: The skill includes high-privilege operations such as database destruction, schema modification, and permission updates via manageSqlDatabase and managePermissions.
  • Sanitization: No specific validation or filtering logic is provided for data retrieved from the database. This surface is inherent to database management functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 7, 2026, 04:25 PM
Security Audit — agent-trust-hub — relational-database-mcp-cloudbase