ClawHub

产品经理

Security checks across malware telemetry and agentic risk

Overview

This is a text-only product-management skill that creates structured product documents and does not request hidden access, execution, credentials, or persistence.

Install if you want a Chinese-first product-management assistant for PRDs, requirements, metrics, and planning templates. Be aware it may activate on general product-planning requests, and avoid sharing confidential roadmap, customer, or regulated business data unless your workspace policy allows it.

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 (2)

Vague Triggers

Medium
Confidence
84% confidence
Finding
The skill description is broad enough to match many ordinary product-related requests, which can cause unintended invocation. Over-broad triggering is risky because it may override a more appropriate skill or steer the conversation into a product-planning workflow the user did not explicitly request, reducing reliability and potentially exposing unrelated context to the skill.

Natural-Language Policy Violations

Medium
Confidence
88% confidence
Finding
The rule '中文优先：所有输出使用中文' hard-codes output language without offering user choice or opt-in. This can cause unsafe or misleading behavior when the user expects another language, especially for requirements, acceptance criteria, or compliance-sensitive content where precision and user comprehension matter.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal