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 is a disclosed Chinese-language study-planning skill that organizes exam revision materials and progress records without executable code, network behavior, or hidden privileged actions.
Before installing, confirm you want a Chinese-language exam sprint workflow and keep any private course files inside the disclosed study workspace. Review generated plans, records, and quizzes yourself, especially where academic integrity rules apply.
Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.
The skill name and full description are written in Chinese and the documented user interaction patterns are Chinese-only, but the file does not state that language is optional or that the skill is intentionally limited to a Chinese-speaking context. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.
The file defines very broad natural-language triggers such as “讲一下”, “给个例题”, “我这里没懂”, and “开始今天任务”, which are common phrases in ordinary educational conversation. This can cause the skill to activate or take over behavior unexpectedly during unrelated or mixed-context chats, leading to unintended instruction routing, loss of user intent fidelity, or interference with other safeguards and agent workflows.