MLOps Automation
Security checks across malware telemetry and agentic risk
Overview
This is a coherent MLOps template skill with normal CI, Docker, and coverage-reporting behavior, but users should review the workflow and supply the missing referenced templates from a trusted source.
Before installing, review the GitHub Actions workflow, decide whether Codecov uploads are acceptable, and only add any missing justfile or Dockerfile templates if you get them from a trusted source. For sensitive repositories, consider pinning third-party GitHub Actions to commit SHAs.
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.