Security audit
Security checks for vulnerabilities and agentic risk
This is a Chinese-language reasoning-template skill with some quality and scoping issues, but no code execution, data access, persistence, or hidden privileged behavior.
Install this only if you want a Chinese-language first-principles reasoning workflow. Expect broad trigger terms and some imperfect exemplar consistency, but the reviewed artifacts do not request sensitive permissions or perform system actions.
The trigger phrases are broad and conceptually generic, such as '第一性原理', '基本元素', and '事实驱动', which can overlap with many normal user requests. This can cause the skill to activate unintentionally and steer unrelated conversations into its prescribed methodology, creating prompt-routing confusion and reducing user control over which skill is applied.
This markdown file presents all headings, labels, and task descriptions in Chinese, and does not mention any option for users to choose another language or explicitly opt into Chinese. Under the language/locale policy, forcing a specific language without user choice can be a natural-language policy violation.
SQP-3 applies to all file types and covers language or locale policy violations. This markdown exemplar is entirely Chinese-language content and does not indicate that users can opt into Chinese, choose another language, or that the skill is intentionally limited to a Chinese-language/regional context.
The manifest describes a skill focused on first-principles reasoning: decomposing problems into irreducible elements, separating facts from assumptions, and rebuilding solutions from basic facts. This file instead contains delivery-phase exemplars for integrity checks, response-time optimization, satisfaction evaluation, improvement suggestions, and continuous optimization, with no first-principles analysis workflow present.
This markdown exemplar presents all instructions, examples, and outputs only in Chinese. Under the policy rule, forcing a specific language without user opt-in can be a natural-language policy violation when no justification or language-selection option is provided.
The file is entirely in Chinese and does not indicate any mechanism to adapt to the user's preferred language or locale. In an agent skill, forcing a single language can cause users or downstream agents to misinterpret instructions, constraints, or outputs, which can degrade safety, correctness, and accessibility even if it is not directly code-execution related.
The document is entirely written in Chinese and implicitly constrains interaction artifacts and outputs to that language, without indicating that language should be selected based on the user's preference. In a general-purpose agent skill, this can cause unintended exclusion, misunderstanding, or degraded task performance when users expect another language, making it a genuine policy/UX safety issue even though it is not an exploitative security primitive.
The skill content and description are entirely in Chinese, and there is no statement that language is user-selectable or that the skill is intended only for a Chinese-language context. This can be a natural-language policy issue when a skill effectively forces one language without explicit opt-in or documented justification.
This file presents all instructions, headings, and examples exclusively in Chinese, which can amount to a language-policy constraint if users are not given an explicit opt-in or alternative locale. The policy for this audit calls for flagging language or locale restrictions unless the skill offers a choice or clearly documents a justified regional scope.
This markdown exemplar presents all instructions, inputs, and outputs exclusively in Chinese, and there is no indication that the user can opt into another language or that the skill is intentionally limited to a Chinese-speaking context. Under the language/locale policy, forcing a specific language without user opt-in can be a natural-language policy violation.
