Feasibility Study
Security checks across malware telemetry and agentic risk
Overview
This is a low-risk company-values coaching skill with no code execution, credentials, persistence, or hidden authority.
This skill appears safe to install for drafting company values and culture guidance. As with any advisory skill, review its suggested values for fit with your own company and avoid treating examples as mandatory policy.
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
67/67 vendors flagged this skill as clean.