ClawHub

Qa Heuristic Checklist

Security checks across malware telemetry and agentic risk

Overview

This is a Chinese QA checklist skill that provides testing heuristics and does not include code, persistence, credential handling, or mutation authority.

Install this if you want Chinese-language QA checklist guidance. Be aware it may activate on broad testing-help requests and may answer in Chinese unless your agent or prompt asks otherwise.

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
87% confidence
Finding
The skill's trigger condition uses broad natural-language phrases like '这个功能怎么测' and '有什么测试要点', which are common in ordinary QA conversations and can cause the skill to activate when the user did not explicitly intend to invoke it. In an agent system, this can lead to unintended prompt injection of the skill's instructions, reducing predictability and potentially overriding more suitable or safer workflows.

Natural-Language Policy Violations

Medium
Confidence
78% confidence
Finding
The skill metadata and content are written to operate in Chinese without any language negotiation or user-consent mechanism. In multilingual environments, this can cause the agent to respond in an unexpected language, leading to misunderstanding, reduced usability, and possible misexecution of testing guidance.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal