ClawHub

张雪峰思维视角 v2.0

Security checks across malware telemetry and agentic risk

Overview

This is a Chinese education and career-planning persona skill with no code or data access; its main risk is that broad trigger words may activate it unintentionally.

Install this if you want an opinionated Chinese education and career-planning lens. Treat its advice as perspective rather than authoritative guidance, and be aware that broad trigger words may invoke the persona when you did not explicitly ask for it.

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 (3)

Vague Triggers

Medium
Confidence
82% confidence
Finding
The trigger list includes very broad terms such as “信息差”, “实用主义”, and “避坑”, which are common concepts that can appear in many unrelated conversations. This can cause the skill to activate outside its intended education/career-planning scope, unexpectedly steering model behavior toward this persona and advice style when the user did not request it.

Natural-Language Policy Violations

Medium
Confidence
75% confidence
Finding
The skill metadata and trigger design are entirely Chinese-centric, with no indication that activation should respect the user’s current language or locale. While not directly enabling code execution or data exfiltration, this can degrade safety and usability by overriding user language expectations and causing unintended language switching during activation.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger phrases are broad, generic terms such as “信息差”, “实用主义”, and “避坑”, which commonly appear in ordinary education, career, and self-improvement conversations. This can cause the skill to activate unintentionally and steer responses into a strong persona-driven framing, increasing the chance of inappropriate, biased, or off-topic guidance in unrelated contexts.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal