data-visualization

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches installation documentation and CLI configuration from the official inference-sh GitHub repository and uses NPM to add the 'belt' CLI tool.
  • [REMOTE_CODE_EXECUTION]: Uses the 'belt app run' command to execute Python code on a remote environment provided by inference.sh. This is used to render charts using libraries like Matplotlib and Numpy based on provided data templates.
  • [COMMAND_EXECUTION]: Provides instructions for local environment setup and chart generation using the 'belt' CLI, including authentication ('belt login') and running application-specific executors.
  • [PROMPT_INJECTION]: The skill facilitates an indirect prompt injection surface by providing templates for code generation that incorporate data inputs. However, within the context of a visualization utility and the specified trusted platform, this is an expected architectural pattern rather than a malicious finding.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 10:27 PM
Security Audit — agent-trust-hub — data-visualization