Security audit
Security checks for vulnerabilities and agentic risk
This skill is a non-executable Chinese-language concept guide for distinguishing Web3/RWA tokenization terms and includes clear boundaries around financial and compliance use.
Installers should understand this is educational concept-classification guidance, not legal, compliance, or investment advice. For actual token issuance, fundraising, or jurisdiction-specific legality, use a dedicated compliance/legal review path.
The manifest description is written entirely in Chinese and frames the skill's usage conditions in Chinese-only terms, while the rest of the skill consistently assumes Chinese-language interaction. There is no statement that the skill supports other languages or that Chinese is an intentional, user-selected locale, which can violate language/locale choice policy.
The test prompts define activation behavior largely through examples and expected outcomes, but they do not encode a crisp, bounded rule for when the skill must activate versus defer. In a routing or orchestration setting, this ambiguity can cause the skill to engage on adjacent finance/compliance prompts and produce classification guidance where the safer behavior would be to hand off to a stricter compliance or implementation skill.
The entire skill test-results content is written in Chinese and describes routing behavior using Chinese trigger examples, but there is no indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking or region-specific audience. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation.
No suspicious patterns detected.
