book-cover-design
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements the principle of least privilege by restricting tool access to
Bash(belt *)within the YAML frontmatter, ensuring the agent can only execute the intended CLI command. - [SAFE]: External references to GitHub (raw.githubusercontent.com) and the service provider (inference.sh) are used for documentation and legitimate service interaction. The GitHub link points to a markdown file for installation instructions rather than an executable script.
- [SAFE]: No evidence of prompt injection, data exfiltration, or obfuscation was found in the instructions or example prompts.
- [SAFE]: The skill instructions correctly identify that AI cannot render text reliably and guide users to use external design tools for typography, which is a safe and standard design practice.
Audit Metadata