Security audit
Referral Loop Design — Turn Customers into a Channel
Security checks across malware telemetry and agentic risk
Overview
This is a simple markdown guidance skill about designing referral programs, with no executable code or hidden authority.
This skill appears safe to install as business-planning guidance. Its external deciqAI and GitHub links are promotional/reference links, so review them separately before relying on those sites, but the skill itself does not execute code or request sensitive access.
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
VirusTotal
64/64 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.
