ClawHub
Back to skill

Security audit

Tailscale Manager

Security checks for vulnerabilities and agentic risk

Overview

This is a read-only Tailscale helper that can reveal tailnet device and identity details, but its behavior is disclosed and aligned with its purpose.

Install only if you are comfortable letting the agent run the local tailscale CLI and show tailnet status, devices, diagnostics, serve status, and whois results. Treat the public IP masking as a useful display safeguard rather than a hard privacy boundary, and prefer explicit prompts such as "tailscale status" or "tailscale devices" over broad tailnet mentions.

SkillSpector

Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill invokes a local Python script that in turn uses the Tailscale CLI, which is a shell-capable operation, but the manifest does not declare corresponding permissions. This creates a transparency and policy-enforcement gap: users or the platform may treat the skill as lower risk than it is, even though it can execute local commands and access sensitive network state.

Static analysis

No suspicious patterns detected.