referrals
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional, providing strategic frameworks and marketing advice without implementing any executable code, shell commands, or network operations.
- [DATA_EXPOSURE]: The skill asks for business metrics such as Customer Lifetime Value (LTV) and Customer Acquisition Cost (CAC). This data gathering is necessary for the skill's primary function of marketing optimization and does not involve unauthorized exfiltration.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to read local context files (e.g.,
.agents/product-marketing.md). While this represents a data ingestion surface, the skill serves an advisory role and lacks dangerous capabilities like command execution or file modification, resulting in a safe configuration.
Audit Metadata