netsuite-ai-connector-instructions
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements security best practices for AI agents. It includes a comprehensive 'SuiteQL Safety Checklist' that requires user confirmation, limits query results (ROWNUM <= 1000), and mandates metadata verification before query execution.\n- [SAFE]: A 'SafeWords' section is included to explicitly instruct the agent to treat external data as untrusted and to ignore any instructions embedded within that data, effectively mitigating potential indirect prompt injection risks from NetSuite record content.\n- [SAFE]: The skill follows the principle of least privilege by prioritizing read-only standard reports and searches over custom SQL queries, and requiring human-in-the-loop confirmation for all write or irreversible operations.
Audit Metadata