Security audit
Umami
Security checks across malware telemetry and agentic risk
Overview
The supplied scan signals are clean and the inspected artifacts do not show hidden, deceptive, destructive, or purpose-mismatched behavior.
This appears safe to install based on the supplied telemetry and inspected artifacts. As with any operational skill, only configure service tokens or API credentials with the minimum permissions needed for the workflows you intend to use.
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
64/64 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.