Security audit

火山引擎DNS免费版

Security checks across malware telemetry and agentic risk

Overview

This DNS management skill is not malicious, but it should be reviewed because it can change live DNS records and its activation scope is broader than its DNS-only purpose.

Review before installing if you manage production domains. Use it only for explicit Volcengine DNS tasks, keep API keys limited in scope, verify existing records before changes, and require manual confirmation for update and delete operations because mistakes can interrupt websites, routing, or email.

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 (2)

Vague Triggers

High

Confidence: 91% confidence
Finding: The trigger condition is so broad that it can cause the agent to invoke this DNS-modifying skill for unrelated coding, debugging, or deployment requests. In a skill with write and exec tools plus destructive DNS operations, overbroad activation increases the chance of unintended record changes, service disruption, or credential use outside user intent.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The skill documents DNS update and deletion capabilities but does not place a clear, prominent warning near those operations about outage risk, misrouting, mail disruption, or rollback requirements. In infrastructure tooling, missing safety warnings and confirmation expectations can lead users or agents to perform destructive changes that impact live services.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.