omg
Security checks across malware telemetry and agentic risk
Overview
This skill is a documentation-only passive monitoring and alerting skill with disclosed request-metadata access and no executable install code.
Before installing, verify the listing identity despite the name/version mismatch, confirm autonomous/model invocation is disabled in your platform, and only configure webhook or email alerts to trusted destinations. Review whether its request-metadata logging and unspecified retention are acceptable for your environment.
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
66/66 vendors flagged this skill as clean.