MLOps
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only MLOps reference skill with no executable components or hidden access requests.
Safe to install as a reference guide. Treat its production deployment, rollback, and monitoring examples as operational advice that still requires normal review, testing, and change-control before applying to real ML systems.
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.