Whitehat Security

Security checks across malware telemetry and agentic risk

Overview

This looks like a legitimate WhiteHat Security integration, but it gives an agent broad authenticated API access, including write and delete-capable proxy requests, without clear approval boundaries.

Install only if you trust Membrane and want an agent to work with your WhiteHat Security data. Use a least-privileged WhiteHat/Membrane connection, review connected-account access periodically, and require explicit approval before any create, update, delete, or raw proxy request.

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: 91% confidence
Finding: The skill explicitly documents a generic proxy request capability with support for POST, PUT, PATCH, and DELETE but does not require confirmation, safety checks, or warnings before data-modifying operations. In an agent setting, this increases the risk of unintended destructive API calls against a live security platform, especially if the model infers or improvises raw requests when higher-level actions are unavailable.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal