Security audit
Token Efficiency
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only productivity skill about reducing token use, with no executable code, credentials, persistence, or hidden access requested.
This appears safe to install as a productivity instruction skill. Users who require detailed audit trails should be aware it encourages shorter narration and sub-agent delegation, so platform logging should remain enabled for tool and sub-agent activity.
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
61/61 vendors flagged this skill as clean.