approval-workflows

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill contains standard documentation and JavaScript (ES5) code snippets for ServiceNow development. All provided code uses official GlideRecord and GlideAggregate APIs for interacting with approval tables.
  • [COMMAND_EXECUTION]: The skill utilizes a toolset (snow_query_table, snow_execute_script, snow_approval_chain_manage) intended for ServiceNow platform administration. These tools are used within their expected scope to query and modify records in a connected ServiceNow instance.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing external data from ServiceNow records.
  • Ingestion points: ServiceNow records retrieved via snow_query_table.
  • Boundary markers: None present in the code snippets.
  • Capability inventory: Subprocess execution via snow_execute_script and data writing capabilities across ServiceNow tables.
  • Sanitization: Standard use of parseFloat and existence checks (e.g., caller.manager) are present in the provided script templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 04:48 PM
Security Audit — agent-trust-hub — approval-workflows