relational-database-mcp-cloudbase

Pass

Audited by Gen Agent Trust Hub on Nov 12, 2026

Risk Level: SAFEDATA_EXFILTRATIONCOMMAND_EXECUTIONPRIVILEGE_ESCALATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DATA_EXPOSURE]: The tool queryMysqlDatabase provides an action="getConnectionInfo" which returns raw database connection details, including host and password, for legacy migration purposes.
  • [COMMAND_EXECUTION]: The skill enables execution of arbitrary SQL commands through manageMysqlDatabase(action="runStatement"), which allows the agent to perform data mutations and schema modifications like DELETE or DROP.
  • [PRIVILEGE_ESCALATION]: The managePermissions tool allows the agent to modify access controls for SQL tables via action="updateResourcePermission", enabling the modification of security policies.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from external database queries which could potentially contain malicious instructions, creating an attack surface when combined with its management capabilities.
  • Ingestion points: Data retrieved from the database via queryMysqlDatabase(action="runQuery").
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands in the retrieved data.
  • Capability inventory: The skill can execute mutating SQL (runStatement), destroy database instances (destroyMySQL), and update permissions (managePermissions).
  • Sanitization: There are no explicit instructions to sanitize or validate data retrieved from SQL queries before the agent acts upon it.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 12, 2026, 02:29 AM