landing-page-design
Pass
Audited by Gen Agent Trust Hub on Apr 25, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: References installation instructions for the 'belt' CLI tool from the inference.sh GitHub repository.
- [COMMAND_EXECUTION]: Utilizes the 'belt' CLI for legitimate operations, including authentication and running remote applications for image generation and web search.
- [PROMPT_INJECTION]: Includes the use of search tools (Tavily, Exa) that fetch content from external websites into the agent's context, serving as a potential surface for indirect prompt injection. This is a standard risk for tools processing untrusted web data.
Audit Metadata