schema-designer
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- [Prompt Injection] (SAFE): No instructions found that attempt to override system behavior or bypass safety constraints.
- [Data Exposure & Exfiltration] (SAFE): The skill uses whodb_tables and whodb_columns to read database metadata. This is appropriate for its stated purpose and does not involve exfiltrating data to external domains or accessing sensitive local files.
- [Remote Code Execution] (SAFE): No patterns for downloading or executing remote code were found.
- [Indirect Prompt Injection] (LOW): The skill reads external data (database schema metadata). While this creates a theoretical surface where a maliciously named table or column could influence the agent, the risk is negligible as the skill only outputs text and DDL suggestions to the user without executing them.
- [Obfuscation] (SAFE): No encoded or hidden content was detected.
Audit Metadata