ClawHub

Research Pro

Security checks across malware telemetry and agentic risk

Overview

Research Pro is a markdown-only Chinese-first research workflow, with no bundled code, installer, credential use, persistence, or hidden behavior.

Install this if you want a Chinese-oriented research workflow assistant. Before allowing it to run experiments, generate or execute code, use datasets, invoke other skills, or coordinate helper agents, review and approve the concrete commands and files involved.

SkillSpector

By NVIDIA
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 (2)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger phrases include very broad terms such as “做研究中” and “论文模式,” which can easily match ordinary academic conversation and unintentionally activate the skill. In an agent setting, accidental invocation can redirect a normal discussion into a multi-step research workflow, causing unwanted behavior, scope expansion, or tool usage without clear user intent.

Natural-Language Policy Violations

Medium
Confidence
82% confidence
Finding
The skill metadata and commands are primarily Chinese-language and appear to assume Chinese interaction by default, without stating any language negotiation or fallback behavior. This can cause user intent mismatch, confusion, or reduced transparency if the surrounding session is in another language, though it is not directly a code-execution or data-exfiltration risk.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal