Philosophy
Security checks across malware telemetry and agentic risk
Overview
This is a simple philosophy guidance skill with no code, hidden actions, credential use, or risky permissions.
This skill appears safe to install for philosophy discussion and teaching support. As with any educational prompt, review whether its teaching style fits your needs, but the artifact does not show risky permissions, hidden execution, credential handling, or external data flows.
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.