Security audit

DNS查询免费版

Security checks for vulnerabilities and agentic risk

Overview

The skill is mainly a DNS lookup helper, but its own instructions also claim unrelated database, coding, file, API, and general command capabilities while requesting command execution access.

Review this skill before installing. It appears intended for DNS queries with dig and does not show malicious code, but its invocation text is overbroad and inconsistent. Only use it if you are comfortable with an agent having command execution access for DNS tasks, and consider narrowing the skill description and capability sections to DNS-only behavior.

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
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 (5)

Description-Behavior Mismatch

Medium

Confidence: 96% confidence
Finding: The manifest description instructs use for database operations, SQL queries, and data storage even though the skill actually documents DNS lookups via dig. This scope mismatch can cause the agent to invoke the skill in unrelated contexts, expanding exec-enabled exposure and leading to unsafe or incorrect tool use under false pretenses.

Intent-Code Divergence

Medium

Confidence: 91% confidence
Finding: The capability text says the skill supports create/query/export operations through input_params, which contradicts the rest of the file describing a single-domain DNS query tool. Overstated capabilities can mislead orchestration logic or users into supplying broader inputs, increasing the chance of unsafe exec flows or unintended handling of files/data outside the DNS use case.

Description-Behavior Mismatch

Medium

Confidence: 90% confidence
Finding: The documented core functions broaden the skill into file processing, API integration, information retrieval, and general command execution, which materially exceeds the stated DNS lookup purpose. In an exec-capable skill, this kind of scope inflation is dangerous because it encourages over-selection and normalizes broader actions than users would expect from a DNS utility.

Vague Triggers

High

Confidence: 97% confidence
Finding: The skill description contains broad, conflicting invocation guidance unrelated to DNS lookup, including database-oriented use cases. Because skill selection often relies on manifest text, this can route unrelated tasks into an exec-enabled tool, creating a prompt-scope vulnerability where the wrong tool is chosen and potentially given unsafe inputs or authority.

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The activation scope lists broad, incoherent keywords such as code generation, programming assistance, testing, and deployment that do not map cleanly to DNS lookup. This weakens trigger boundaries and makes accidental or policy-bypassing invocation more likely, especially given the skill has exec access.

Static analysis

No suspicious patterns detected.