The Agent Skills Directory

[SAFE]: The skill instructions are purely diagnostic and design-oriented, providing a framework for creating referral loops and reward structures. No malicious commands or privilege escalation attempts were identified.
[EXTERNAL_DOWNLOADS]: The skill references a repository (github.com/SkeneTechnologies/skene-skills) owned by the skill author for extended auditing capabilities. This is a vendor-owned resource used for its stated purpose and does not represent a security risk.
[INDIRECT_PROMPT_INJECTION]: The skill contains logic to ingest data from a user's codebase by searching for referral-related strings (e.g., invite, share, reward). While this represents a data ingestion surface, the skill is focused on analysis and lacks execution capabilities that would allow for harmful exploitation of this surface.

referral-program