landing-page-design

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references external installation instructions and configuration files from the inference.sh repository on GitHub. These are documented as standard setup procedures for the required CLI tools.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for ingesting external data through search tools such as Tavily and Exa.
  • Ingestion points: Competitor landing page examples and conversion statistics are retrieved from the web via belt app run tavily/search-assistant and belt app run exa/answer.
  • Boundary markers: There are no specific delimiters or instructions provided to separate untrusted search results from the agent's core instructions.
  • Capability inventory: The skill utilizes the Bash(belt *) toolset to execute CLI-based inference and search applications.
  • Sanitization: No explicit sanitization or filtering of the external search data is specified before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 10:16 AM