WorkOS

Security checks across malware telemetry and agentic risk

Overview

This is a coherent WorkOS MCP connection skill that clearly discloses OAuth access and workspace read/write capabilities, with no hidden execution or persistence in the artifacts.

Install only if you want an agent to access and modify your WorkOS workspace. Review requested OAuth scopes, confirm destructive actions such as deletes, archives, revokes, or bulk updates, and do not paste authorization codes, access tokens, or refresh tokens into chats, logs, screenshots, or scripts.

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
88% confidence
Finding
The manual OAuth section instructs users to handle authorization codes, access tokens, and refresh tokens directly, including copying a code from a browser back into a client, but does not warn that these values are sensitive secrets. In practice, this increases the chance that users paste tokens into logs, chats, shell history, screenshots, or insecure scripts, which could enable account or workspace access if intercepted.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal