customer-persona

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the belt CLI for market research and image generation, providing installation instructions that point to the platform's official GitHub repository.- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves searching the web and processing the results to build customer profiles, which introduces a surface for indirect prompt injection from search results.
  • Ingestion points: The skill retrieves external market data and pain point analysis from the Tavily and Exa search APIs.
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore' commands when processing the external search data.
  • Capability inventory: The skill is restricted to using the belt command-line tool to run specific search and image generation applications.
  • Sanitization: There is no evidence of specific sanitization or validation logic applied to the external search content before it is incorporated into the persona template.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 05:53 PM
Security Audit — agent-trust-hub — customer-persona