visual-selector

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill contains no executable code or scripts. It consists entirely of markdown documentation, decision logic, and JSON-formatted reference templates for Power BI visuals.
  • [SAFE]: No evidence of prompt injection, data exfiltration, or obfuscation was found. The instructions are focused on mapping data fields to visual buckets and providing layout recommendations.
  • [SAFE]: The skill's architecture relies on static rules and local reference files. No external dependencies, remote script downloads, or network operations were detected.
  • [SAFE]: While the skill processes user-provided query intent for visual overrides, it lacks any dangerous capabilities (such as shell access, file modification, or network requests) that could be exploited through indirect prompt injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 08:14 PM
Security Audit — agent-trust-hub — visual-selector