Unifi

• Outcome: Pass
• Latest audit: May 28, 2026 at 12:24 PM UTC
• Version:
  3.2.1

Overview

This is a disclosed UniFi network management skill; it uses sensitive API keys and can change live network settings, but the behavior matches its stated purpose and is not hidden.

Install only if you want an agent to view and manage your UniFi environment. Use dedicated, revocable API keys with the least privileges available, protect config.json or prefer protected environment variables, configure gateway_fingerprint for local access, and manually review any set-* command before running it because it can disrupt connectivity.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 93% confidence
• Finding: The skill clearly uses environment variables, file-based configuration, and network access to manage UniFi infrastructure, but the manifest does not declare corresponding permissions. That creates a trust and review gap: operators may grant and run a skill with infrastructure-changing capabilities without explicit visibility into what resources it can access.

Missing User Warnings

High

• Confidence: 96% confidence
• Finding: The documentation explicitly permits local HTTPS connections to proceed without certificate verification when no fingerprint is configured. That enables man-in-the-middle attacks on the local network, allowing an attacker to intercept API keys and tamper with management traffic to the UniFi gateway.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The documentation includes live configuration-changing commands such as setting WLAN, DNS, radio parameters, and client labels, but it does not prominently warn that these operations mutate production network settings. In an agent-driven context, that omission increases the risk of accidental disruptive changes to connectivity, security posture, or client behavior through routine use.

Missing User Warnings

Medium

• Confidence: 87% confidence
• Finding: Several commands perform live configuration changes on WLANs, radios, clients, and network DNS immediately after parsing CLI arguments, with no confirmation prompt, dry-run mode, or explicit high-risk warning. In a network-management skill, this increases the chance of accidental misconfiguration that can disrupt connectivity, weaken wireless security, or change name resolution for an entire site.

VirusTotal

64/64 vendors flagged this skill as clean.