landing-page-design
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
beltCLI for generating images, performing web searches, and rendering HTML to images. The command access is restricted in the YAML frontmatter to only allow executions starting withbelt, which is a security best practice for scoping tool access. - [EXTERNAL_DOWNLOADS]: The skill refers to installation instructions on GitHub (
inference-sh/skills) and suggests installing thebelt-sh/clivianpx. These external references are transparent and directly related to the skill's primary functionality for interacting with theinference.shservice. - [DATA_EXFILTRATION]: No unauthorized data access or exfiltration patterns were detected. The
belt logincommand is a standard authentication procedure for the integrated API service. - [PROMPT_INJECTION]: The skill contains instructional content and tool usage examples without any attempts to bypass agent safety filters or override core behavioral instructions.
Audit Metadata