ui-builder-patterns

Pass

Audited by Gen Agent Trust Hub on Feb 23, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [SAFE]: The skill is a technical guide and code repository for ServiceNow UI Builder development and contains no malicious instructions or obfuscated code.\n- [COMMAND_EXECUTION]: The skill integrates with tools such as snow_execute_script_with_output and snow_workspace_create to perform legitimate ServiceNow development tasks.\n- [PROMPT_INJECTION]: Evaluation of the indirect prompt injection surface:\n
  • Ingestion points: External data from ServiceNow records is ingested via snow_query_table and GraphQL Data Brokers (SKILL.md).\n
  • Boundary markers: No specific delimiters or markers are defined in the templates to separate record data from logic.\n
  • Capability inventory: The skill can execute server-side scripts and modify workspace configurations via its included tools (SKILL.md).\n
  • Sanitization: No sanitization logic is provided in the templates for processing external record content.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 23, 2026, 08:26 PM