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 Markdown-only strategy and persuasion coaching skill with visible ethical cautions and no code, tools, persistence, or data access, though its persuasion framing could be misused.
Install this only if you want a Chinese/English Guiguzi-style negotiation and persuasion coach. Use it for transparent, lawful negotiation or strategy planning, and avoid applying it to deception, coercion, intimate relationships, political manipulation, or exploiting vulnerable people.
Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.
Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.
Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.
Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.
Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.
Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.
Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.
Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.
The trigger set is broad and overlaps with ordinary discussion of negotiation, persuasion, and strategy, which can cause the skill to activate in contexts where the user did not specifically request this manipulative-strategy persona. Unintended activation matters here because the skill provides tactics for probing, influencing, and exploiting interpersonal weaknesses, so accidental invocation can steer conversations toward coercive framing.
This section operationalizes manipulative tactics such as praise-then-control, probing emotional weaknesses, and exploiting fissures in alliances, while the policy framing is too weak to prevent harmful use. In context, the skill is explicitly designed for persuasion, lobbying, and interpersonal games, which increases the likelihood that users apply it to coercion, deception, workplace abuse, or targeted social engineering.
The file presents the skill primarily in Chinese throughout its title, descriptions, scenarios, and lookup table, with only limited English glosses in section headers. Because there is no statement offering language choice or explaining that the skill is intended only for Chinese-speaking users or a region-specific audience, it creates a natural-language locale policy concern.
The entire template is written in Chinese and includes no note that the skill is China-specific or that users may choose another language. Under the policy rule, a skill that effectively mandates a specific language without opt-in can be a locale-policy violation.
This markdown file contains user-facing instructional text primarily in Chinese while also forcing English phrasing such as 'Mind-Reading Step-by-Step Template' and 'legacy'. Under the language/locale policy, presenting a fixed language mix without offering the user a choice can be a natural-language policy issue.
The document is written entirely in Chinese and presents itself as a general-purpose persuasion template, but it does not state that Chinese is optional or that the skill is intended only for a Chinese-speaking context. Under the language/locale policy criterion, a skill that effectively requires a specific language without opt-in can be a policy concern.