Onethread

Security checks across malware telemetry and agentic risk

Overview

This looks like a legitimate Onethread integration, but it gives an agent broad authenticated ability to change or delete support data without clear confirmation boundaries.

Install only if you trust Membrane and want an agent to access your Onethread workspace. Use the least-privileged account available, prefer discovered Membrane actions over raw proxy requests, and require the agent to show the exact method, endpoint, payload, and expected effect before creating, updating, deleting, or automating Onethread data.

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: 93% confidence
Finding: The skill explicitly documents a generic proxy request capability supporting POST, PUT, PATCH, and DELETE, but does not warn that these operations can modify or delete remote Onethread data. In an agent context, this increases the chance that the model may issue powerful raw API requests without adequate confirmation, validation, or scoping, especially when prebuilt actions do not cover the use case.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal