customer-persona
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs users to install a third-party CLI tool using
npx skills add belt-sh/cliand references installation guidelines hosted on a GitHub repository (https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md). - [COMMAND_EXECUTION]: The skill utilizes the
Bashtool to executebeltCLI commands. These commands are used to perform authenticated market research via search assistants (Tavily, Exa) and generate persona avatars using image generation models (FalAI). - [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it ingests untrusted data from external search results to populate persona templates.
- Ingestion points: Data enters the context via
belt app runcommands targetingtavily/search-assistantandexa/search(SKILL.md). - Boundary markers: None are explicitly used in the provided command examples to separate search results from the agent's internal logic.
- Capability inventory: The skill has access to the
Bashtool to run CLI applications. - Sanitization: There is no evidence of automated sanitization for the search results before they are processed by the agent.
Audit Metadata