query-generation

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides curl command templates in SKILL.md for validating table schemas and testing queries against a ServiceNow instance. These are standard administrative patterns for API interaction.
  • [PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection by transforming natural language requirements into structured queries and scripts.
  • Ingestion points: Natural language descriptions provided by the user (as described in SKILL.md).
  • Boundary markers: None explicitly defined for user requirements.
  • Capability inventory: Tool capabilities include SN-Create-Record, SN-Query-Table, and generating GlideRecord/GlideAggregate scripts for the agent to use.
  • Sanitization: The skill includes an explicit 'Best Practices' section advising developers to 'Avoid eval() in dynamic queries' and 'Never construct queries from unvalidated user input'.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 01:34 PM
Security Audit — agent-trust-hub — query-generation