Security audit
SOTA Agent
Security checks across malware telemetry and agentic risk
Overview
The available scan inputs show no concrete malicious or suspicious behavior, and the pending VirusTotal result is not a negative signal by itself.
This looks acceptable to install based on the available evidence. VirusTotal was still pending, so treat that as incomplete telemetry rather than a warning; review the skill’s requested permissions and only provide credentials or tokens that match the skill’s stated purpose.
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.
Static analysis
No suspicious patterns detected.
