referrals

Pass

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is entirely instructional and informational. It provides marketing advice, program design loops, and email templates without any executable scripts or command-line operations.
  • [SAFE]: No network operations or data exfiltration risks were identified. The skill references well-known third-party marketing tools (such as Stripe, Rewardful, and PartnerStack) for implementation, but does not perform any automated connections to them.
  • [SAFE]: Data ingestion is limited to reading local context files (like .agents/product-marketing.md) to tailor its advice to the user's product. This pattern is safe as the skill lacks any dangerous capabilities (e.g., shell access, file writing, or network requests) that could be triggered by malicious content in those files.
  • [SAFE]: No prompt injection or obfuscation patterns were detected. The instructions follow standard marketing expertise patterns and encourage legitimate growth strategies.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 14, 2026, 09:32 AM