Referral Program
v1.0.0When the user wants to create, optimize, or analyze a referral program, affiliate program, or word-of-mouth strategy. Also use when the user mentions 'referr...
⭐ 0· 98·0 current·0 all-time
byMario Karras@mariokarras
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name/description match the SKILL.md content: guidance on referral vs affiliate programs, incentives, metrics, launch checklist, templates and examples. It doesn't request unrelated binaries, cloud credentials, or external services beyond recommending common referral/affiliate tools.
Instruction Scope
Instructions tell the agent to read a local product context file if present (.agents/product-marketing-context.md or .claude/product-marketing-context.md). This is reasonable for tailoring recommendations, but it means the skill will look for and consume workspace files when available. Nothing in the instructions directs reading unrelated system files, environment variables, or exfiltrating data to unknown endpoints.
Install Mechanism
No install spec and no code files — the skill is instruction-only, so nothing is written to disk or downloaded during install.
Credentials
The skill declares no required env vars, credentials, or config paths. The guidance mentions third-party tools and integration ideas but does not request API keys or secrets itself.
Persistence & Privilege
always:false (default) and the skill can be invoked autonomously (disable-model-invocation:false), which is the platform default. Autonomous invocation combined with the skill's low access footprint is not a concern here, but users who prefer manual control should disable autonomous invocation in agent settings if available.
Assessment
This skill appears to do exactly what it says: provide referral and affiliate program advice and templates. Before installing, consider: 1) The skill will look for and read product-marketing-context.md files in the agent workspace if present — remove or inspect any sensitive data in those files first. 2) It requests no credentials and has no install step, so it won't write binaries or ask for secrets. 3) If you prefer to review suggestions before they run automatically, disable autonomous invocation in your agent settings. Otherwise this skill is low-risk and proportionate to its purpose.Like a lobster shell, security has layers — review code before you run it.
latestvk973s1d67b4xh1zdhmc1npy1jh836438
License
MIT-0
Free to use, modify, and redistribute. No attribution required.