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 Chinese advertising-copy methodology skill with no executable code, persistence, network behavior, or sensitive access.
Installers should know this skill may be invoked too broadly because of generic trigger words, so it is best suited for users who frequently ask for Chinese advertising or brand-copy work. It does not appear to run code or access private data.
Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.
The trigger terms include very broad words like 'skill', '优化', '品牌', and 'brand', which are likely to appear in ordinary user conversation and unrelated tasks. This can cause accidental invocation, making the agent inject persuasive advertising methodology into contexts where the user did not intend to use this skill, increasing prompt-collision and behavioral hijacking risk.
The skill name, description, and instructional content are entirely in Chinese, and the file does not indicate that the user can choose another language or that the skill is intentionally limited to a Chinese-language audience. Under the language/locale policy, forcing one language without opt-in can be a policy concern.