ClawHub
Back to skill

Security audit

available-domain-search

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed remote domain search tool, with a minor over-trigger risk from a broad activation keyword.

Install only if you intend to use AgentPMT for live domain availability or suggestion searches. Be aware that calls cost 3 credits and send the domain names or business-description query to AgentPMT; avoid including sensitive launch plans unless that sharing is acceptable. The publisher should narrow the standalone "domains" trigger to reduce accidental use.

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 activation keyword list includes the single broad term "domains," which is likely to over-trigger this skill for many unrelated requests involving domains in general, not specifically domain registration or availability search. In an agent environment, overly broad triggers can cause unintended remote tool invocation, unnecessary data exposure to a third-party service, and accidental spending of credits.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.