customer-persona

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references documentation and tool installation from raw.githubusercontent.com/inference-sh and npx, which are standard for the skill's operational environment and trace back to the tool's official resources.- [COMMAND_EXECUTION]: Uses the belt CLI to perform searches and generate images. These operations are within the scope of the skill's defined allowed-tools configuration.- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-defined search queries and image prompts. While this represents a standard attack surface for data processing, the risk is localized to the specific search/generation context and lacks access to sensitive system resources.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:19 PM
Security Audit — agent-trust-hub — customer-persona