Security audit

多搜索聚合器

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward multi-provider search skill that sends user queries to configured search APIs, with no evidence of hidden execution, persistence, or destructive behavior.

Install this only if you are comfortable sending search terms to Tavily, Brave, and/or Perplexity under your own API keys. Avoid using it for secrets, private project names, credentials, or sensitive personal data, and configure only the providers you intend to use.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The skill is explicitly a multi-provider search aggregator, but the description does not clearly warn that user queries will be transmitted to third-party services such as Tavily, Brave, and Perplexity. This matters because search queries may contain sensitive prompts, internal project names, credentials, or personal data, and sending them externally without clear notice can cause confidentiality and compliance issues.

Missing User Warnings

Medium

Confidence: 86% confidence
Finding: The script forwards user search queries to one or more third-party APIs without any explicit user-facing warning at runtime or consent mechanism. In an agent skill context, users may assume a local tool invocation, so sensitive prompts, internal names, or proprietary terms could be unintentionally disclosed to external providers.

VirusTotal

38/38 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.