ClawHub
Back to skill

Security audit

研究代理助手免费版

Security checks across malware telemetry and agentic risk

Overview

This is a research-document helper that writes local Markdown/PDF research notes and uses search, with some wording that users should scope carefully but no evidence of deception or harmful behavior.

Install only if you want an agent to perform web research and create/update local research files. Keep research topics and source folders scoped, do not provide a callback URL unless you trust the endpoint, and review any PDF export or package-install commands before allowing them.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
86% confidence
Finding
The trigger condition is overly broad and mismatched to the skill's purpose, which can cause the agent to activate in unintended contexts such as generic file-processing requests. In an agent environment with read/write/exec tools, incorrect activation increases the chance of unnecessary file operations or command execution beyond what the user expected.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill describes internet-based research and includes optional callback_url support without a clear privacy notice explaining what data may leave the local environment. This creates a risk that user prompts, research content, or metadata could be transmitted to third-party services or arbitrary endpoints without informed consent.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill describes internet-based research and includes optional callback_url support without a clear privacy notice explaining what data may leave the local environment. This creates a risk that user prompts, research content, or metadata could be transmitted to third-party services or arbitrary endpoints without informed consent.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.