customer-persona

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references documentation and installation guidelines hosted on GitHub (raw.githubusercontent.com/inference-sh/skills).
  • [COMMAND_EXECUTION]: The skill instructions utilize the belt CLI tool to interact with external search and AI services (Tavily, Exa, Fal.ai). These operations are performed via the Bash tool.
  • [SAFE]: The skill configuration employs the allowed-tools restriction (Bash(belt *)), which limits the agent's command-line capabilities to the specific CLI tool required for its primary functions, reducing the risk of unauthorized command execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 10:39 PM
Security Audit — agent-trust-hub — customer-persona