Security audit

域名DNS管理免费版

Security checks for vulnerabilities and agentic risk

Overview

This DNS management skill is mostly coherent, but it should be reviewed because it can make live DNS changes and includes unrelated trigger terms that could activate it in the wrong context.

Review this skill before installing if you would give it real DNS or registrar credentials. Use only least-privilege tokens for the intended domain, require the agent to show the current DNS state and proposed diff before any change, and remove or ignore the unrelated project-management trigger language.

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

Confidence: 83% confidence
Finding: The skill declares an overly broad activation scope with unrelated keywords such as project management and team collaboration, which can cause an agent to invoke this DNS-management skill in irrelevant contexts. In an agent ecosystem with exec/write tools and credentialed DNS operations, overbroad triggering increases the chance of unintended destructive actions against domains or infrastructure.

Missing User Warnings

Medium

Confidence: 89% confidence
Finding: The skill provides credential setup and live DNS-changing commands without a clear warning that these actions are sensitive, can disrupt service, and should require explicit user confirmation. In context, this is more dangerous because the skill has exec capability and operates on production DNS, where a mistaken or premature command can redirect traffic, break email, or cause outages.

Static analysis

No suspicious patterns detected.