referrals
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of marketing strategy documentation and templates. It does not perform any automated actions, command execution, or network requests.
- [EXTERNAL_DOWNLOADS]: The documentation references well-known third-party services (e.g., Stripe, Rewardful, PartnerStack) for implementing referral programs. These are informational references only and do not involve automated downloading or execution of remote code.
- [DATA_EXFILTRATION]: The skill asks the user to provide business metrics such as Customer Acquisition Cost (CAC) and Lifetime Value (LTV) to tailor its advice. This data collection is manual and consistent with the skill's primary function, with no evidence of automated exfiltration to third-party domains.
- [PROMPT_INJECTION]: The instructions do not contain attempts to override agent behavior, bypass safety filters, or extract system prompts.
Audit Metadata