Back to skill

Security audit

Zhang Lei Perspective

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only Chinese-language investing and business perspective skill with broad triggers, but no code execution, credential access, persistence, or hidden behavior.

Install this if you want a Chinese-language Zhang Lei-style framework for business and long-term value analysis. Be aware it may activate on generic moat or long-term-thinking prompts, and it should not be treated as personalized financial advice or as statements from Zhang Lei himself.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The activation guidance is broad enough to trigger on generic phrases like '有护城河吗' or '从长期想想', which can cause the skill to activate outside its intended investment/thought-framework context. Over-broad routing can override a better-matched skill or apply persona-constrained advice in unrelated situations, reducing reliability and potentially producing inappropriate financial/business framing.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill hard-codes a specific response style and effectively assumes a Chinese-language persona presentation without giving the user a language choice or documenting why that constraint is necessary. This can misalign with user expectations, reduce accessibility, and in multilingual environments cause the assistant to ignore the user's preferred language or communication needs.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file defines the skill entirely in Chinese and prescribes a specific Chinese-language expression style, including wording, tone, and examples. Because the instructions do not offer any language or locale choice, they create a natural-language policy issue by implicitly forcing a specific language output without user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

This markdown file presents its title and all visible content in Chinese, with no indication that language selection is optional or that the skill is explicitly limited to a Chinese-language context. Under the language/locale policy rule, forcing a specific language without opt-in can be a policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

This markdown file is entirely written in Chinese, including the title and all content, with no indication that the skill is region-specific or that users can choose another language. Under the language/locale policy rule, forcing a specific language without opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.