landing-page-design
Pass
Audited by Gen Agent Trust Hub on Nov 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions to download a CLI installation script from the vendor's official GitHub repository and uses npx to add dependencies. These actions facilitate the setup of the tools required for the skill.
- [COMMAND_EXECUTION]: Demonstrates how to use the belt CLI to execute specific remote tasks like image generation and web searches. The execution environment is restricted by the allowed-tools configuration to the belt command prefix.
- [INDIRECT_PROMPT_INJECTION]: The skill incorporates external data via search applications (tavily/search-assistant, exa/answer). This creates a standard surface for indirect prompt injection from untrusted web content.
- Ingestion points: Web search results processed by the belt CLI.
- Boundary markers: None present in the command examples.
- Capability inventory: File generation and information retrieval via vendor-hosted applications.
- Sanitization: Managed by the vendor's platform and CLI processing layers.
Audit Metadata