email-design

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the belt CLI tool (associated with the author's ecosystem inference.sh) to perform common tasks such as generating images from HTML and fetching AI-generated banners. These are documented actions consistent with the skill's primary purpose.
  • [EXTERNAL_DOWNLOADS]: The skill references an installation script for the belt CLI from raw.githubusercontent.com/inference-sh/skills/. As this is the author's own repository and a prerequisite for the skill's functionality, it is considered a legitimate dependency.
  • [PROMPT_INJECTION]: No prompt injection attempts or bypass instructions were detected. The skill contains standard educational and technical instructions for email design.
  • [DATA_EXFILTRATION]: No sensitive file access or unauthorized network transmissions were found. Network operations are limited to the vendor's own CLI tools and established services.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 04:08 PM
Security Audit — agent-trust-hub — email-design