customer-persona

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS] The skill references and provides installation instructions for the belt CLI tool from npx and a configuration file from a public GitHub repository (raw.githubusercontent.com/inference-sh/skills/...). Per the [TRUST-SCOPE-RULE], these are recognized as standard developer tooling and configuration from a service provider and are considered safe.
  • [COMMAND_EXECUTION] The skill provides example commands for using the belt CLI to run market research (tavily/search-assistant) and generate images (falai/flux-dev-lora). These are functional examples for the skill's stated purpose and do not perform unauthorized file access, network exfiltration, or privilege escalation.
  • [NO_CODE] The skill consists entirely of markdown instructions and documentation; it does not ship with any executable scripts or binaries.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 05:09 PM
Security Audit — agent-trust-hub — customer-persona