diagram-to-code
Security checks across malware telemetry and agentic risk
Overview
The available scan evidence is clean and does not show hidden, destructive, or overbroad behavior requiring Review.
This version can remain in the normal install path based on the available evidence. As with any skill, users should still review its displayed instructions and only provide credentials or file access that clearly match the task they asked it to perform.
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.