skills/tul-sh/skills/customer-persona/Gen Agent Trust Hub

customer-persona

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides structured instructions and examples for creating customer personas using research-backed data.
  • [EXTERNAL_DOWNLOADS]: The skill references the infsh CLI tool and prompts the user to install it via npx skills add inference-sh/skills@agent-tools. This is a vendor-owned resource (inference.sh) and is considered safe within the context of the skill's functionality.
  • [COMMAND_EXECUTION]: The skill uses the Bash(infsh *) tool to execute market research and image generation commands. These commands (infsh app run) target specific apps like tavily/search-assistant, falai/flux-dev-lora, and exa/search, which are standard tools for search and AI generation. There are no signs of arbitrary or malicious command execution.
  • [DATA_EXFILTRATION]: No patterns of sensitive data access or unauthorized external transmission were found. The network operations are limited to the intended research and generation functions via the vendor's CLI.
  • [PROMPT_INJECTION]: The instructions focus on persona creation and do not contain any patterns designed to bypass AI safety guidelines or override system prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 08:25 AM