Ai Coach
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only AI coaching skill that matches its stated purpose and does not ask for code execution, credentials, or hidden access.
Safe to install as a coaching prompt skill. Be selective about sharing sensitive personal, fitness, wellbeing, career, or productivity information, and only enable listed integrations if you trust those connected tools and understand what data they can provide.
SkillSpector
By NVIDIA
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
66/66 vendors flagged this skill as clean.