ClawHub
Back to skill

Security audit

Domain availability API built for AI agents. Check single domains, explore names across .com/.io/.ai/.dev/etc, filter by budget, get smart suggestions. Returns proper JSON/TXT with correct Content-Type headers.

Security checks across malware telemetry and agentic risk

Overview

This is a legitimate-looking domain registrar skill, but it lets an agent spend money and change live domain infrastructure without clear final-approval and impact-warning guardrails.

Install only if you want an agent to interact with ClawDaddy for real domain purchases and live DNS administration. Require explicit approval before any purchase, DNS deletion or overwrite, nameserver change, transfer preparation, lock change, or autorenew change, and keep management tokens in a dedicated secret store rather than ordinary chat or long-term memory.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (2)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill describes a direct purchase flow for domain registration, including payment and successful completion, without requiring an explicit user confirmation step immediately before the irreversible paid action. In an agent context, this increases the risk of unintended charges and registrations because domain purchases are financially consequential and may not be easily reversible.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The management instructions allow DNS, nameserver, and settings changes but do not warn that incorrect updates can break website resolution, email delivery, verification records, or transfer/lock protections. In an autonomous-agent setting, omission of these cautions can lead users to approve or agents to perform high-impact configuration changes without understanding operational consequences.

VirusTotal

40/40 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.