data-visualization

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references installation scripts and related skill definitions hosted on the vendor's official GitHub repository (inference-sh/skills). These are legitimate resources provided by the skill author for tool setup and expansion.
  • [COMMAND_EXECUTION]: The skill uses the 'belt' CLI, which is explicitly listed in the allowed-tools metadata, to execute visualization code. These commands interact with the vendor's official applications ('python-executor' and 'html-to-image') to render charts and dashboards.
  • [PROMPT_INJECTION]: The content is strictly instructional and focused on data visualization best practices. It does not contain instructions aimed at bypassing safety filters or overriding system prompts. The use of code interpolation is a standard functional component of this visualization utility.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 02:28 AM
Security Audit — agent-trust-hub — data-visualization