Ml Pipeline Starter
Security checks across malware telemetry and agentic risk
Overview
This is a sparse ML pipeline guide with purpose-aligned command examples, but users should verify any external script before running deployment commands.
Install is reasonable if you want ML pipeline guidance, but do not run ./ml-pipeline.sh or deploy to production unless you know where that script came from, have reviewed it, and have confirmed the target 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.