referral-program
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions specify loading a local context file (
.agents/product-marketing-context.md) and ingesting user input regarding business models and metrics. While this represents a data ingestion surface, the skill is designed purely for advisory purposes and lacks capabilities such as command execution, network access, or file-writing tools that could be exploited by malicious data. - [SAFE]: The skill content is educational and strategic. It recommends well-known third-party services (Rewardful, Tolt, PartnerStack, Stripe) for implementation and follows standard business design patterns without any signs of obfuscation, remote code execution, or persistence mechanisms.
Audit Metadata