logo-design-guide
Pass
Audited by Gen Agent Trust Hub on Nov 14, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references an installation script for the
beltCLI fromraw.githubusercontent.com/inference-sh/skills/. This targets a well-known service for infrastructure related to the skill's primary function and is documented neutrally. - [COMMAND_EXECUTION]: The skill provides numerous Bash examples for using the
beltCLI to run AI image generation models. These commands are typical for the stated purpose of the skill and do not involve sensitive file access or dangerous operations. - [REMOTE_CODE_EXECUTION]: Mentions
npx skills addto install related tools. This is a standard package management operation for the specific platform the skill is designed for. - [INDIRECT_PROMPT_INJECTION]: While the skill takes user-defined subjects to generate prompts, it does not ingest untrusted external data (like web pages or API results) or have dangerous capabilities like file-writing or network exfiltration that would create an exploitable surface.
Audit Metadata