Smoove

Security checks across malware telemetry and agentic risk

Overview

This Smoove skill appears legitimate, but it gives an agent broad authenticated access that can change or delete business data without clear approval guardrails.

Install only if you intend to let an agent act in your Smoove account through Membrane. Before any create, update, or delete request, require the agent to show the exact action or endpoint, target connection, parameters, and expected impact; revoke the Membrane/Smoove connection when no longer needed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
Findings (1)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill explicitly documents arbitrary proxy requests to the Smoove API, including POST, PUT, PATCH, and DELETE, without any warning that these operations can modify or delete live remote data. In an agent setting, this increases the chance of unintended destructive actions because the documentation normalizes direct API use without requiring user confirmation or emphasizing mutation risk.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal