Security audit
Nudge Theory
Security checks across malware telemetry and agentic risk
Overview
This is a static educational skill for applying nudge theory, with no executable code, persistence, credential use, or hidden runtime authority.
This skill is safe to install as a thinking and coaching aid. Users should still apply its own ethical checks carefully because nudge design can become manipulative if used to steer people toward outcomes that serve the designer rather than the chooser.
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.