a skill for Persona Metadata Framework
Security checks across malware telemetry and agentic risk
Overview
No supplied or locally accessible evidence showed hidden, destructive, or data-stealing behavior, but the target artifact itself was not available for full review.
This looks acceptable based on the available signals, but install only after reviewing the actual skill text and metadata because the exact target artifact was not present in the workspace for independent confirmation.
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
65/65 vendors flagged this skill as clean.