Tp4
- Category
- MCP Tool Poisoning
- Confidence
- 98% confidence
- Finding
声明描述的是一个具有明确认知分析与优化用途的技能,但代码块只是一个示例/占位 Python 脚本,唯一行为是输出“This is an example script for zhua-metacognition”。它没有读取输入、分析思维过程、监控状态、应用策略优化,也没有任何与声明用途相符的实现。因此描述与实际行为存在明显的实质性不匹配。
- Content
Security audit
Security checks for vulnerabilities and agentic risk
This skill is a low-risk metacognition prompt framework, though its packaged helper files are placeholders and some referenced files are missing.
Install only if you want a Chinese-language metacognition prompt framework. Expect incomplete helper tooling unless the missing scripts and referenced documents are added later.
声明描述的是一个具有明确认知分析与优化用途的技能,但代码块只是一个示例/占位 Python 脚本,唯一行为是输出“This is an example script for zhua-metacognition”。它没有读取输入、分析思维过程、监控状态、应用策略优化,也没有任何与声明用途相符的实现。因此描述与实际行为存在明显的实质性不匹配。
The manifest description and primary skill content are written entirely in Chinese and framed as the skill's default operating mode, with no indication that users may opt into another language. Under the policy, language-specific behavior should either provide user choice or clearly justify the locale restriction.