Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 88% confidence
- Finding
文件从标题开始即全部以中文呈现，未说明这是面向特定中文地区用户的限定场景，也未提供其他语言或用户选择。根据规则，未获用户同意而强制单一语言属于自然语言政策风险。
- Content
Security audit
段永平长期检查
Security checks for vulnerabilities and agentic risk
Overview
This is a disclosed investment-analysis checklist with no network, credential, persistence, or trading capability, but its investment recommendations should be treated cautiously.
Review the investment outputs as a checklist, not as instructions to buy, hold, or sell. The skill does not trade, access accounts, or send data externally, but its simplified scoring and directive recommendations can still be misleading without independent research or professional 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
- MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
- 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 (6)
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The skill gives affirmative long-term holding guidance such as '建议：长期持有' and frames a pass/fail investment test, but it does not include a clear, prominent disclaimer that the output is not financial advice and may materially affect user finances. In an investment context, users may over-rely on this simplified framework and make consequential portfolio decisions without understanding the limitations, uncertainty, or need for professional advice.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The file's top-level description and all user-facing guidance are written exclusively in Chinese, presenting the skill as operating in that language by default. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly justified, which is not present here.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The recommendation labels, action guidance, and printed usage instructions are all hardcoded Chinese strings shown to the user. Because the skill does not offer a language choice or state a justified region-specific constraint, this enforces a specific language on all users.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The entire template is written in Chinese and does not indicate that users may choose another language or locale. Under the policy rule for language/locale, this is a natural-language policy issue unless the locale restriction is explicitly justified or optional.
- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 98% confidence
- Finding
The script claims to print a usable '使用说明', including the instruction on line L168, but that line uses unescaped nested double quotes and makes the module fail to parse before it can run. This is an intent-code divergence because the code presents runtime guidance that the program cannot actually deliver in its current form.
- Content
Static analysis
No suspicious patterns detected.