ClawHub
Back to skill

Security audit

Ai Desktop Researcher

Security checks across malware telemetry and agentic risk

Overview

This skill is a structured market-research checklist that uses public web research and does not install code, persist, or access private data.

Installers should expect this skill to make market-research requests more structured and likely to involve web searches, source comparison, and longer reports. For quick lookups, users may need to explicitly ask for a brief answer rather than the full research protocol.

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
89% confidence
Finding
The skill description includes broad trigger phrases such as generic requests to 'research this market' or '查一下XX市场', which can overlap with ordinary user requests and cause the skill to activate more often than intended. Over-broad activation increases the chance that the agent is routed into a rigid research workflow when the user wanted a lighter task, creating scope creep, unnecessary web access, or undesired instruction precedence from the skill.

VirusTotal

57/57 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.