referral-program
Pass
Audited by Gen Agent Trust Hub on Feb 24, 2026
Risk Level: SAFENO_CODEEXTERNAL_DOWNLOADS
Full Analysis
- [SAFE]: No security issues were identified. The content is purely instructional and follows safe practices for AI agent skills. The skill attempts to read a local context file (.claude/product-marketing-context.md) to provide personalized marketing advice, which is a benign operation for this use case.
- [NO_CODE]: The skill does not include any executable scripts or code files (e.g., Python, Node.js, or Shell), eliminating the possibility of remote code execution, unauthorized system commands, or dependency-based attacks.
- [EXTERNAL_DOWNLOADS]: The skill references several well-known industry tools and platforms such as Stripe, HubSpot, Segment, Rewardful, and Mention Me as part of its strategic recommendations. These are documented neutrally as well-known marketing services and do not involve the download or execution of untrusted external code.
Audit Metadata