The Agent Skills Directory

[SAFE]: The skill is entirely informational and contains no malicious code, obfuscation, or persistence mechanisms. All logic is focused on marketing strategy and program design.
[DATA_EXPOSURE]: The skill instructions include reading a local file (.agents/product-marketing-context.md) to gather existing business context. This is a standard functional behavior for providing personalized marketing advice and does not involve unauthorized access or exfiltration of sensitive system data.
[REMOTE_CODE_EXECUTION]: No remote code execution patterns, package installations, or dynamic code generation were detected. References to third-party platforms like Rewardful, Tolt, and Stripe are provided as informative links or pointers to other integration skills.
[PROMPT_INJECTION]: The skill contains no instructions designed to bypass agent safety filters or override system-level directives.

referral-program