Mlflow
Security checks across malware telemetry and agentic risk
Overview
This MLflow skill is a disclosed Membrane-based integration that needs network access and authentication to manage MLflow data, with no evidence of hidden or malicious behavior.
Before installing, users should be comfortable installing the Membrane CLI, logging into Membrane, and allowing the agent to run user-directed MLflow actions or proxy API requests against the selected MLflow connection. Prefer discovered Membrane actions before raw proxy requests, and review any mutating or delete-style operation before execution.
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
65/65 vendors flagged this skill as clean.