ClawHub
Back to skill

Security audit

Tailscale

Security checks across malware telemetry and agentic risk

Overview

This Tailscale skill is mostly coherent, but some high-impact actions are left untagged even though the safety instructions say untagged actions may run directly.

Review this before installing if the connected Tailscale account has admin privileges. Use it only where you are comfortable delegating tailnet administration through OOMOL, and require explicit confirmation for any action that changes users, devices, DNS, keys, webhooks, policy, secrets, or sends external events, even when the skill does not tag that action as write or destructive.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The description instructs the agent to use this skill for ANY Tailscale request and instead of calling the API directly, which is an overly broad trigger surface for a high-privilege integration. Because the skill exposes many write and destructive actions, broad activation increases the chance the agent invokes it inappropriately or without sufficient task-specific scoping, leading to unintended reads, state changes, or deletions in a user's tailnet.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.