Back to skill

Security audit

Mental Models Master | 顶级思维模型工具箱

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only decision-analysis skill with broad activation language, but it does not include code, persistence, credential access, network access, or data-changing authority.

Install this if you want a Chinese-language mental-model framework for investment and decision analysis. Be aware that its activation language is broad, so it may shape many 'important decision' conversations even outside investing; it should not replace qualified financial, legal, medical, or safety advice.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
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 (4)

Vague Triggers

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The description says the skill should be used for 'any important problem/decision,' which is overly broad and can cause the agent to invoke this skill in many unrelated contexts. Overbroad auto-activation increases prompt-routing risk, can overshadow more appropriate domain-specific skills, and may inject investment-oriented reasoning into sensitive decisions without user intent.

Content

No source excerpt is available for this finding.

Vague Triggers

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The mandatory rule that the model 'must' invoke the skill for every important problem or decision creates ambiguous, compulsory behavior without clear boundaries. This can hijack normal assistant behavior, reduce user control, and cause systematic over-application of the skill even when the task does not warrant this framework.

Content

No source excerpt is available for this finding.

Vague Triggers

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger list uses generic phrases like '怎么分析', '应该怎么做', 'complex problem', and 'uncertainty,' which are common across many benign conversations. Such broad matching can cause frequent unintended activation, effectively turning the skill into a catch-all behavior modifier rather than a narrowly scoped tool.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The manifest description is written entirely in Chinese and the skill instructions consistently prescribe Chinese-language interaction patterns without any opt-in or language choice. This can violate language/locale policy when users have not selected Chinese as their preferred language.

Content

No source excerpt is available for this finding.