Multi-Agent Sandbox

• Outcome: Review
• Latest audit: May 29, 2026, 9:23 PM
• Version:
  1.0.0

Overview

The skill is a coherent setup guide, but it asks users to create persistent network bridges and broad agent/session access that deserve careful review before use.

Install only if you need this advanced multi-agent setup and can administer Docker, systemd, Discord bots, Tailscale, and SSH safely. Use dedicated low-privilege bot and VPS accounts, prefer named agent allowlists over wildcards, limit session history/spawn access, verify and pin SSH host keys instead of disabling checking, and remove the systemd bridge services when the sandbox is no longer needed.

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: 98% confidence
• Finding: The skill explicitly documents SSH usage with `-o StrictHostKeyChecking=no`, which disables host authenticity verification and makes users vulnerable to man-in-the-middle attacks. In this skill's context, SSH is used to reach a shared VPS over a network bridge, so suppressing host key checks weakens one of the main protections for that channel.

VirusTotal

66/66 vendors flagged this skill as clean.