Jumpcloud

• Outcome: Review
• Latest audit: May 29, 2026 at 9:37 PM UTC
• Version:
  1.0.2

Overview

This JumpCloud skill is not deceptive, but it gives an agent broad identity-management action and raw API authority without clear confirmation guidance for high-impact changes.

Install only if you intend to let the agent operate against a real JumpCloud tenant through Membrane. Before any create, update, delete, policy, command, group membership, or access-control change, require the agent to show the exact action or API request, affected resources, and expected impact, then wait for explicit approval.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The skill provides detailed instructions for discovering, running, and proxying JumpCloud actions, including potentially destructive administrative operations, but does not warn about sensitivity or require confirmation for write/delete actions. In an identity and device management context, this omission increases the chance that an agent could make harmful changes to users, groups, devices, policies, or authentication-related resources without adequate user awareness.

VirusTotal

65/65 vendors flagged this skill as clean.