Security audit
Security checks for vulnerabilities and agentic risk
This is a markdown-only storytelling methodology skill with no executable code, network access, credential use, or persistence.
Install this if you want a Chinese-language storytelling and hero-journey framework for transforming ideas into narrative-derived solutions. Be aware that the trigger list is broad, so you may want to invoke it explicitly only for storytelling or narrative-structure tasks.
The trigger list contains broad terms such as “故事叙述”, “叙事生成”, and especially “meta-skill-system”, without clear scope boundaries, exclusions, or disambiguation rules. This can cause accidental or overly broad activation in unrelated contexts, leading the agent to load and apply the skill when the user did not intend it, which may distort outputs or override more appropriate behavior.
The skill is documented entirely in Chinese with no language negotiation, fallback, or explicit opt-in for non-Chinese users. In multilingual environments this can cause users or orchestrating agents to misunderstand the skill’s behavior, constraints, and permission model, increasing the chance of unintended invocation or incorrect execution.
This markdown file presents all instructions and examples exclusively in Chinese, which can amount to a language-policy violation when no user opt-in or justification is provided. The policy for this audit requires flagging natural-language constraints that force a specific language without offering choice.
This markdown file is entirely framed as a Chinese-language skill exemplar, with headings, process steps, and output templates all specified in Chinese and no indication that users may choose another language. Under the policy rules, a skill that effectively imposes a specific language without opt-in can be a natural-language policy violation.
The title and the entire requirements document are written exclusively in Chinese, presenting the skill requirements as mandatory methodology without any indication that users may choose another language. Under the policy, forcing a specific language without user opt-in is a natural-language locale violation unless the constraint is explicitly justified.
This markdown exemplar presents all instructions, headings, inputs, and outputs exclusively in Chinese. Under the policy criteria, forcing a specific language without user opt-in can be a natural-language policy violation when no language choice or justification is provided.
This markdown file uses only Chinese headings, inputs, processes, and outputs, which can amount to forcing a specific language or locale without offering the user a choice. The stated policy requires flagging language-policy issues unless the skill explicitly offers opt-in or documents a justified locale constraint.
This markdown file contains all headings and operational descriptions in Chinese and does not mention any option to use another language. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern.
