Mental Models Cn

Security checks across malware telemetry and agentic risk

Overview

This is a Chinese mental-models reference skill with broad activation phrases and some investment examples, but it does not show hidden data access, persistence, or unsafe automatic actions.

Install is reasonable if you want Chinese mental-model and business-analysis reference material. Be aware that it may trigger on broad analysis phrases, and treat investment or asset-allocation content as general educational framing rather than financial advice.

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: 92% confidence
Finding: The trigger list contains very generic phrases such as '如何分析', '用什么模型', and '系统思考' that are likely to overlap with ordinary user prompts unrelated to this specific skill. This can cause unintended activation, routing user requests into the skill unexpectedly, which may degrade reliability, expose users to irrelevant guidance, and create prompt-scope confusion across the agent ecosystem.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The guide provides specific portfolio actions such as increasing stocks, using leverage, holding cash, or buying long-duration bonds, but does not clearly state that this is general educational content rather than personalized financial advice. In a skill triggered by users seeking analysis frameworks and decision models, these directives can be followed as actionable recommendations despite market, suitability, and loss risks.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal