referrals
Pass
Audited by Gen Agent Trust Hub on Jul 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely composed of instructional content and templates for referral and affiliate marketing. No executable code, shell scripts, or obfuscated payloads were detected.
- [DATA_EXPOSURE]: The skill instructs the agent to gather business-specific information such as customer Lifetime Value (LTV) and Customer Acquisition Cost (CAC). This data collection is strictly for the consultative purpose of the skill and does not involve exfiltration to external servers.
- [EXTERNAL_DOWNLOADS]: The skill mentions various industry-standard third-party tools (e.g., Rewardful, Tolt, Stripe, PartnerStack) as implementation recommendations for the user. These are not downloaded or executed by the agent itself.
- [INDIRECT_PROMPT_INJECTION]: The skill reads from local context files like
.agents/product-marketing.md. While this is an ingestion point for potentially untrusted data, the skill lacks any dangerous capabilities (such as file writing or command execution) that could be exploited via indirect injection.
Audit Metadata