Security audit
Security checks for vulnerabilities and agentic risk
This is a topic-focused religious teaching skill with limited citation lookup behavior and no evidence of hidden execution, persistence, credential use, or destructive actions.
Install this if you want Chinese-language Gelug/Tsongkhapa-framed Buddhist teaching with strict citation expectations. Be aware it may activate for broad related topics and may answer in a fixed Chinese doctrinal style unless the host agent or user explicitly redirects language and tone.
The trigger policy is overly broad and explicitly instructs invocation whenever a user's question merely touches the topic, even without an explicit request. This can cause the skill to override user intent, increase unnecessary skill activation, and route unrelated conversations into a rigid persona or instruction set that the user did not ask for.
The style instructions are written as mandatory output behavior in Chinese, which can amount to forcing a specific language or locale. The file lists multiple supported languages at L020, but it does not state that the user may choose the response language or that Chinese is required for a justified region-specific use case.
The file defines the skill’s entire response style, examples, and required closings exclusively in Chinese, with no instruction to detect or honor the user’s preferred language. This can cause the agent to ignore user language expectations, reducing usability, accessibility, and informed consent, and may mislead users into receiving important safety or doctrinal limitations in a language they cannot understand.
The skill mandates a fixed stylistic and linguistic presentation without checking the user's preferred language, tone, or accessibility needs. While not a classic security flaw, it can degrade user control and increase the chance of deceptive or unwanted persona-driven responses, especially when combined with broad auto-invocation.
This markdown file presents all instructional and descriptive content exclusively in Chinese, and there is no natural-language indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking audience. Under the language/locale policy rule, forcing a single language without user opt-in can be a policy concern.
