social-media-carousel

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references external resources for installation and documentation.
  • Recommends installing the belt-sh/cli tool using npx.
  • Fetches installation instructions from the inference-sh GitHub repository.
  • [COMMAND_EXECUTION]: The skill utilizes the belt CLI tool to perform several operations.
  • Executes belt login to authenticate with the platform.
  • Runs belt app run to process HTML templates into images via a remote service.
  • Uses shell loops to batch generate multiple slides for a carousel.
  • [DATA_EXFILTRATION]: While the skill sends data to a remote service (inference.sh), the data consists of user-defined HTML templates and design prompts required for the skill's primary function. There is no evidence of accessing or exfiltrating sensitive local files or environment variables.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 10:16 AM