Loyjoy

Security checks across malware telemetry and agentic risk

Overview

This appears to be a real LoyJoy integration, but it gives an agent broad authenticated ability to call LoyJoy API endpoints, including write and delete methods, without clear built-in approval limits.

Install only if you trust Membrane and intend an agent to access your LoyJoy account. Before any POST, PUT, PATCH, or DELETE request, require the agent to show the exact endpoint, method, and payload and get explicit approval; use least-privileged LoyJoy access and revoke the Membrane connection when finished.

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: 92% confidence
Finding: The skill explicitly documents a generic proxy request capability with support for mutating HTTP methods like POST, PUT, PATCH, and DELETE, but does not require confirmation, scope checks, or user-facing warnings before impactful operations. In an agent setting, this increases the risk of unintended data modification or deletion against the LoyJoy API, especially when available actions do not cover the use case and the agent falls back to raw requests.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal