ClawHub

Liu Qiangdong Perspective V2

Security checks across malware telemetry and agentic risk

Overview

This appears to be a prompt-only business persona skill with an activation-scope quality issue, not evidence of malware or unsafe system access.

Install only if you want the assistant to adopt a Liu Qiangdong/JD-style business lens. Be aware it may activate from generic phrases about JD, self-operated retail, cost, efficiency, or experience; disable or narrow the triggers if you want neutral business analysis by default.

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
93% confidence
Finding
The trigger list includes broad business concepts such as '成本效率体验' and '自营模式' that are common in ordinary business discussions and not uniquely tied to this skill. This can cause unintended activation, making the assistant adopt a fixed founder persona in contexts where the user did not actually request roleplay, which can distort advice and reduce reliability.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The supplemental trigger list adds more ambiguous, high-collision phrases like '成本效率体验', '自营模式', and '京东怎么做' without any exclusion rules or disambiguation logic. In a business-advice setting, these phrases are likely to appear naturally, increasing accidental activation risk and causing the model to respond in-character when neutral analysis would be safer.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal