Tp2
- Category
- MCP Tool Poisoning
- Confidence
- 85% confidence
- Finding
Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.
- Content
Security audit
Security checks for vulnerabilities and agentic risk
This skill is a Chinese-language guidance pack for academic branding and does not show hidden execution, data access, persistence, or credential use.
Install this if you want Chinese-language guidance on academic influence, personal academic branding, and industry-facing expert positioning. Be aware that its triggers are fairly broad and the included script/reference/asset files are placeholders, so it is more of a static advice template than an automated tool.
Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.
从提供的代码看,这只是一个示例模板:定义了 main() 并打印 “This is an example script for academic-brand-builder”,注释中也明确说明是 placeholder,等待未来补充逻辑。它没有处理学术品牌、个人IP、专家形象、学术营销、资源对接等任何实际能力,也没有体现与触发词相关的业务逻辑。因此,代码实际行为与声明用途存在明显不一致,属于材料性目的不匹配。
The activation description says the skill triggers whenever researchers need to improve influence, build a personal brand, connect with industry resources, or transition to industry expert roles. These conditions are broad, overlapping, and lack exclusion criteria, so many general career-development requests could unintentionally invoke the skill.
Triggers such as “个人IP”, “专家形象”, and “学者转型” are short, generic phrases that can appear in many unrelated conversations. The manifest does not constrain context or provide negative examples, increasing the risk of accidental activation.
The manifest description and the rest of the skill content are entirely in Chinese, and there is no indication that users may request responses in another language. Under the stated policy, a language constraint should either be optional for the user or explicitly justified as region-specific.