Mattr

Security checks across malware telemetry and agentic risk

Overview

This MATTR skill is a coherent integration, but it gives an agent broad authenticated access to identity tenant data without clear approval safeguards for changes or deletes.

Install only if you trust Membrane and want an agent to operate against MATTR through that service. Use a least-privileged MATTR account or tenant, prefer discovered Membrane actions over raw proxy calls, and require the agent to show the endpoint, method, payload, tenant, and expected effect before any create, update, patch, or delete operation.

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

Findings (1)

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The skill explicitly documents running arbitrary actions and direct proxy requests against the MATTR API without warning that these operations may create, update, or delete tenant resources. In an agent setting, this increases the chance of unintended state-changing or irreversible operations being performed without adequate user confirmation or risk framing.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal