data-visualization

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONDYNAMIC_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references and fetches installation instructions for the belt CLI from the inference-sh GitHub repository and suggests adding related skills via npx.
  • [REMOTE_CODE_EXECUTION]: It uses the belt command-line utility to run code in remote environments, specifically infsh/python-executor and infsh/html-to-image, which execute user-provided code strings to generate visualization files.
  • [COMMAND_EXECUTION]: The skill instructs the agent to use shell commands (belt login, belt app run, npx skills add) to interact with external services and install necessary tooling.
  • [DYNAMIC_EXECUTION]: The visualization recipes involve generating Python scripts at runtime that utilize matplotlib and numpy to create and save images like revenue.png, line-chart.png, and heatmap.png.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:20 PM
Security Audit — agent-trust-hub — data-visualization