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 bilingual Confucian self-cultivation and leadership guidance skill with no code execution, data access, or persistence behavior.
This skill appears safe to install if you want Confucian or Great Learning-based guidance for reflection, leadership, or planning. Be aware that its broad triggers may make it show up in ordinary coaching or management conversations even when you did not explicitly ask for Confucian framing.
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 phrases are broad, generic life-coaching and management topics, which can cause the skill to activate in many unrelated conversations. Over-broad invocation increases the chance of unintended routing, context capture, or policy interference, especially when multiple skills may compete for common topics like planning, leadership, or decision-making.