Security audit
Security checks for vulnerabilities and agentic risk
This skill is a Chinese-language workflow/template skill with broad framing, but the artifacts are disclosed Markdown instructions with no hidden code, data access, persistence, or destructive behavior.
Install only if you want a Chinese-language structured thinking framework for complex tasks. Treat its identity-field and consensus-network outputs as methodology scaffolding, not as factual authority, and ask for visible reasoning summaries when using it on important decisions.
The manifest description is entirely in Chinese and presents the skill behavior in a single language with no indication that users may choose another language. Under the language/locale policy, this can be a violation unless the skill explicitly offers opt-in language choice or states a justified region-specific constraint.
The skill claims it can treat essentially any task as an 'identity emergence field' without clear activation boundaries, exclusions, or safety gating. Overbroad triggers increase the chance the skill will activate in inappropriate contexts, override more specialized controls, or apply opaque transformation logic to sensitive tasks such as security, privacy, or high-stakes decision support.
The skill documentation gives conflicting instructions about transparency: earlier text says field interactions are hidden by default unless the user asks, while the '事实纪律' section says the derivation process must be shown to the user. In an agent setting, contradictory disclosure rules can cause inconsistent handling of reasoning or internal process details, leading either to unintended leakage of internal deliberation or to opaque outputs that undermine auditability and safe operation.
The entire skill reference is presented only in Chinese, including the title, task domains, and exemplar descriptions, with no indication that users may choose another language or locale. Under the policy for natural-language violations, this constitutes a language/locale constraint that is not documented as optional or region-specific.
The activation trigger '任务需要多身份协作' is extremely broad and does not define boundaries, exclusions, or authorization criteria for when additional 'identity fields' should be activated. In an agent skill, vague activation conditions can cause the workflow to expand its scope unnecessarily, apply hidden internal role simulation to unintended tasks, and make behavior less predictable or controllable.
The entire skill exemplar is written as a Chinese-only template and all example inputs/outputs are specified in Chinese, with no indication that users may choose another language. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly justified.
The document presents the skill entirely in Chinese and the execution protocol at L03 does not offer any language choice or opt-in. Under the stated policy, forcing a specific language without user selection is a natural-language policy violation unless the locale constraint is explicitly documented and justified.
The title and the entire requirements checklist are written as prescriptive instructions in Chinese, and the document does not indicate that other languages are allowed or that Chinese is optional. Under the policy rule, forcing a specific language without user opt-in is a natural-language locale violation.
This markdown exemplar presents all instructions, inputs, and outputs exclusively in Chinese, which can amount to a language/locale policy issue when no user opt-in or scope justification is provided. The file does not state that it is intended only for Chinese-speaking users or a region-specific workflow.
This markdown exemplar presents all instructions, inputs, and outputs solely in Chinese, but does not state that the skill is intended only for Chinese-speaking users or offer any language/locale option. Under the language/locale policy, forcing a single language without user opt-in can be a natural-language policy violation.
