referral-program

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is composed exclusively of instructional markdown content and configuration data. It contains no executable scripts, shell commands, or functions that perform network operations.
  • [SAFE]: References to external platforms like Stripe, Rewardful, and HubSpot are restricted to well-known services and are used neutrally to suggest implementation tools.
  • [SAFE]: The skill checks for a local file .agents/product-marketing-context.md to gather product information. While this represents a data ingestion surface (ingestion points: SKILL.md; boundary markers: absent; capability inventory: none; sanitization: absent), the skill's capabilities are limited to providing business advice, and no mechanism for command execution or data exfiltration based on this input was found.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 10:39 PM