The Agent Skills Directory

[SAFE]: The skill is entirely composed of informational markdown files and a YAML configuration file. No executable code, scripts, or binary files are present.
[SAFE]: The instructions do not contain any prompt injection attempts, obfuscated content, or hardcoded credentials.
[SAFE]: The skill does not perform network operations or access sensitive system directories. References to local files like .claude/product-marketing-context.md are for context-gathering purposes within the agent's environment and do not involve data exfiltration.
[SAFE]: Mentioned external tools and platforms, such as Stripe and Rewardful, are standard industry services provided as suggestions for the user and are not automatically invoked or controlled by the skill code.

referral-program