relational-database-mcp-cloudbase
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [Indirect Prompt Injection] (SAFE): The skill allows the agent to read data from a database which could theoretically contain malicious instructions. This is mitigated by the skill's instructions for the agent to verify data manually and confirm actions with the user. 1. Ingestion points: executeReadOnlySQL results. 2. Boundary markers: Not specified. 3. Capability inventory: executeWriteSQL and writeSecurityRule. 4. Sanitization: Procedural verification by the agent.
- [Command Execution] (SAFE): The skill describes tools for executing SQL. Since this is the primary purpose and includes safety warnings for destructive operations, it is considered safe for its intended use.
- [No Code] (SAFE): The skill contains no executable scripts or configurations, reducing the risk of hidden malicious behavior.
Audit Metadata