widget-coherence

Pass

Audited by Gen Agent Trust Hub on Feb 23, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill consists of documentation, best practice checklists, and reference code for ServiceNow development. The code examples follow standard API usage and do not contain hidden or malicious logic.
  • [PROMPT_INJECTION]: The skill interprets natural language user requests to generate or modify code artifacts, which creates a surface for indirect prompt injection.
  • Ingestion points: User requests regarding widget creation, fixing, or optimization (SKILL.md).
  • Boundary markers: Absent.
  • Capability inventory: Includes tools for artifact modification and deployment such as snow_edit_artifact, snow_deploy, and snow_update.
  • Sanitization: The skill does not provide explicit instructions for sanitizing or validating user-generated input before code generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 23, 2026, 08:30 PM