QSearch Agent

Security checks across malware telemetry and agentic risk

Overview

This is a simple user-triggered web search skill with disclosed external search-provider use and no evidence of hidden access, persistence, or destructive behavior.

Install only if you are comfortable sending search terms to external search providers. Avoid sensitive queries, and independently verify important links, financial information, downloads, and safety-critical results because the skill's filtering and reliability claims are not enforceable guarantees.

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 (1)

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The skill declares slash-command triggers (/sp, /search, /找, /搜) but the example dialogue also implies activation from free-form natural language like '帮我搜一下茅台股票'. That ambiguity can cause unintended invocation, routing ordinary conversation into web search behavior and broadening the skill’s execution surface beyond what users and orchestrators expect.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal