ClawHub

Nex Domains

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed local domain portfolio tool; its network checks, Cloudflare sync, local database, and removal command match the stated purpose, though users should use credentials and deletion commands carefully.

Install only if you want a local domain inventory and monitoring CLI. Use a least-privilege Cloudflare token for sync, keep registrar credentials protected, confirm intent before running remove, and be mindful that exports may contain client, cost, DNS, and portfolio details.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Vague Triggers

Medium
Confidence
85% confidence
Finding
The trigger phrases are broad terms like "domain," "DNS," "SSL," and "certificate," which are common in normal conversation and likely to cause unintended skill activation. In a skill with shell, network, env, and file-write capabilities, overbroad triggering raises the risk of the agent selecting this skill in contexts where the user did not intend domain scans, API-backed syncs, or local state changes.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill documents a remove command that deletes tracked domains but does not warn that it is destructive or recommend confirmation before use. This is risky because an agent could execute the command from a casual request or misunderstanding, leading to silent loss of locally tracked portfolio data and operational visibility.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The remove command deletes a domain immediately after lookup, with no confirmation prompt, dry-run, or force flag separation. This creates a real safety issue because a mistyped command, automation bug, or untrusted higher-level agent invocation can permanently remove tracked domain data and associated records without giving the user a chance to abort.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal