Ml Ops
Security checks across malware telemetry and agentic risk
Overview
This skill is a plain MLOps checklist and workflow guide, with no code that runs or accesses user data.
Reasonable to install as an MLOps planning aid. Users should still apply their own production, compliance, and privacy review before following its advice for regulated ML systems or workflows involving sensitive data.
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.