Security audit
Security checks for vulnerabilities and agentic risk
This is a Markdown-only Buddhist study curriculum skill with no code execution, credential access, network behavior, or persistence.
Installers should understand that this skill is mainly written in Chinese and is intended for Buddhist curriculum planning, not general doctrinal debate or personal religious authority. It appears safe from a security standpoint, but users may want clearer language and routing notes if they operate in multilingual or multi-skill environments.
The skill is written almost entirely in Chinese and does not provide a language choice, fallback, or explicit opt-in for non-Chinese users. In practice this can cause users or upstream agents to misunderstand scope, constraints, or safety-relevant caveats, leading to incorrect routing or misuse of the skill rather than direct code execution or data compromise.
The trigger list uses very broad, high-frequency terms such as '禅' and '禅宗', which can cause the skill to activate for general discussion rather than explicit curriculum-planning requests. This can lead to incorrect routing, reduced reliability, and unintended exposure of users to a prescriptive learning-path skill when they only wanted comparison, debate, or general explanation.
The trigger list is broad and consists mostly of short topic keywords without clear activation constraints, which can cause the skill to be invoked for loosely related Buddhist queries rather than explicit curriculum-planning requests. In this context the content is not directly harmful, but over-triggering can misroute user requests, suppress more appropriate skills, and create prompt-routing confusion that could be abused indirectly.
The trigger list includes broad domain terms like '华严', '法界', and '贤首' without requiring planning-oriented intent, so the skill could be invoked for general discussion, comparison, or historical questions rather than curriculum requests. This can cause unintended routing, leading to scope confusion and lower-quality or misleading responses, though it does not directly create code-execution or data-exfiltration risk.
The trigger list uses broad terms like '净土', '念佛', and '弥陀' without clear activation boundaries, disambiguation rules, or negative examples. This can cause the skill to activate on general Buddhist discussion rather than explicit curriculum-planning requests, leading to incorrect routing, over-collection of user context, or bypass of more appropriate skills such as comparison or debate flows.
The trigger list includes very broad, high-frequency terms such as '空' and '中道' that can appear in many unrelated Buddhist or general-language queries. This can cause the skill to activate outside its intended scope, leading to misrouting, confused responses, and reduced reliability of downstream agent behavior.
The trigger list is broad and unconstrained, mixing tradition names, practice terms, texts, and teacher names without exclusions or intent qualifiers. This can cause the agent to invoke this skill for requests that are comparative, biographical, definitional, or debate-oriented rather than curriculum-planning, leading to incorrect routing and potentially biased or unsafe guidance in contexts where a different skill should handle the request.
The trigger list is broad and consists mainly of domain keywords without clear activation constraints or negative examples, so the skill may activate for general doctrinal discussion rather than only curriculum-planning requests. In an agent-routing context, this can cause misclassification, sending users to a sequenced-learning skill when they intended comparison, debate, or simple explanation, which degrades reliability and can suppress safer or more appropriate handlers.
This markdown file contains natural-language instructional content exclusively in Chinese, and there is no indication that users can opt into another language or that the skill is intentionally restricted to a Chinese-speaking audience. Under the language/locale policy check, forcing a specific language without opt-in can be a policy violation.
