book-cover-design
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides legitimate design guidance, including genre conventions, sizing, and layout zones, matching its stated purpose.
- [COMMAND_EXECUTION]: Shell commands are restricted via the
allowed-toolsfrontmatter to thebeltCLI tool, which is a security best practice for limiting an agent's execution environment. - [EXTERNAL_DOWNLOADS]: The skill references an external installation guide for the required CLI tool hosted on GitHub (
inference-sh/skills). This reference is for instructional purposes and does not involve direct automated execution of untrusted remote code. - [DATA_EXFILTRATION]: No evidence of sensitive data harvesting or unauthorized network communication was found. The skill uses standard CLI authentication patterns for its intended service.
- [OBFUSCATION]: The content is clear and readable with no hidden characters, encoded strings, or homoglyph attacks detected.
- [PROMPT_INJECTION]: The instructions do not contain attempts to bypass safety filters or override agent behavior.
Audit Metadata