Security audit
Security checks for vulnerabilities and agentic risk
This skill is a text-only brand-avatar generator with no executable code, persistence, data access, or hidden high-impact behavior.
Install this if you want a Chinese-language brand persona/DID generator. Non-Chinese users should expect Chinese templates unless the agent adapts them, and users should provide only the brand/address details they intend to include in the generated identity report.
The invocation guidance says to 'wake up this SKILL' and provide a brand name, which is a very broad activation condition with no explicit trigger phrase, scope limit, or confirmation boundary. In agent environments, vague activation language can cause accidental or unintended invocation in unrelated conversations, increasing the chance the skill runs on insufficient context or against user intent.
The skill explicitly addresses the agent in Chinese and all required interaction/output templates are Chinese-only, with no user language negotiation or fallback. This can exclude users, cause misunderstanding of instructions or outputs, and create unsafe execution contexts if a user assumes the skill will operate in another language while the agent follows embedded Chinese-only constraints.
All user-facing instructions and examples are presented only in Chinese, and the document does not mention any option to use another language. This can be a natural-language policy issue when a skill implicitly forces a specific language without user opt-in or documented justification.
No suspicious patterns detected.
