Vext

Security checks across malware telemetry and agentic risk

Overview

This Vext skill is a plausible integration, but it gives an agent broad authenticated control over Vext data without clear confirmation steps for write or delete actions.

Install only if you trust Membrane and need agent access to Vext. Use the least-privileged Vext account or workspace possible, prefer discovered Membrane actions over raw proxy calls, and require the agent to show the endpoint, method, parameters, and expected effect before any POST, PUT, PATCH, DELETE, bulk update, or workflow automation.

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 instructs use of direct proxy HTTP requests, including state-changing methods like POST, PUT, PATCH, and DELETE, without requiring confirmation or warning about side effects. In an agent setting, this can enable unintended modification or deletion of Vext data, especially when the model falls back to raw API calls instead of safer scoped actions.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal