Security audit
Security checks for vulnerabilities and agentic risk
This is a markdown-only knowledge-auditing skill with a Chinese-oriented default prompt, and I found no hidden code, persistence, or data-exfiltration behavior.
Before installing, note that this skill is aimed at producing evidence-audit cards and appears to answer in Chinese by default. Use it with documents you intentionally provide or connector outputs you trust; it does not show signs of automatic local file access or hidden background behavior.
The skill description is entirely in Chinese and all example prompts are written only in Chinese, which indicates a language-specific interaction expectation without any stated opt-in or alternative language support. Under the policy rule, forcing a specific language without user choice is a natural-language policy violation unless clearly justified as region-specific.
This markdown file contains the skill’s user-facing description, announcement copy, and marketplace text primarily in Chinese. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly documented and justified, which is not present here.
The description lists only Chinese example invocations, which can imply a language-specific activation or usage expectation. Because the file does not state that the skill is China-specific or offer multilingual alternatives, this appears to violate the language/locale policy criterion.
The natural-language output examples and preferred wording are exclusively Chinese, which can steer the skill to respond in a specific language by default. The file does not indicate that the user can choose another language or that the locale restriction is required for a region-specific use case.
The default prompt describes use on broad categories like "my notes, docs, research, or connector outputs" without any explicit activation boundaries, exclusion conditions, or narrow trigger phrases. In a manifest file, this kind of open-ended invocation scope can cause unintended matches with common document-review requests.
The prompt ends with "answer in Chinese," which imposes a language choice unconditionally. This is a natural-language policy issue because it forces a specific output language without offering the user a choice or documenting a justified locale constraint.
The description is written entirely in Chinese and does not indicate that language selection is optional or that the skill is intended only for a Chinese-language audience. A fixed language without opt-in can violate language/locale policy expectations when the skill is distributed broadly.
This markdown file mixes English instructional text with sample output phrases exclusively in Chinese, which can implicitly steer the skill toward a specific language. Under the policy, forcing or preferring a specific language without user opt-in is a natural-language policy violation.
The instruction explicitly prefers the Chinese phrase 目前最稳的判断 over 最终结论, which imposes a specific language choice in the skill's output guidance. This is a natural-language policy issue because the file does not offer the user a language option or explain why Chinese is required in this context.
The release theme is presented entirely in Chinese, which can constitute a language/locale policy issue when a skill artifact imposes a specific language without offering user choice or documenting a justified regional scope. There is no indication in this file that the Chinese-only phrasing is optional or tied to a region-specific requirement.
This manifest file describes the skill's purpose in broad functional terms but does not specify when it should be invoked, what phrases should trigger it, or any exclusion conditions. For manifest files, missing trigger specificity can cause the skill to be matched too broadly in routing or discovery contexts.
