Openai

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed OpenAI integration through Membrane, with normal account-access risks but no evidence of hidden or malicious behavior.

Install this only if you trust Membrane and want it to manage delegated access to your OpenAI account. Prefer listed Membrane actions over raw proxy requests, confirm before deleting files or using POST/PUT/PATCH/DELETE calls, and avoid sending sensitive prompts, files, or organization data unless the user explicitly approves that use.

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 encourages direct proxy HTTP requests to arbitrary OpenAI API paths and describes automatic authentication/header injection, but provides no guardrails around sending sensitive user, system, or tenant data. In an agent setting, this can enable overbroad data transmission to external endpoints or unsafe custom calls that bypass safer prebuilt actions and review points.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal