Security audit
Security checks for vulnerabilities and agentic risk
This is a Chinese medical-record-writing reference skill made of Markdown text, with no executable behavior, network access, persistence, or hidden privilege use found.
Before installing, treat this as a 2015 China/Anhui medical-record documentation reference. Verify current local laws, hospital policy, and original scans for important use, especially because the skill discloses OCR and table-layout limitations. It should not be treated as current medical, legal, or compliance advice outside that context.
The manifest says to use the skill when the user asks about several example phrases and then broadly extends this to '等病历书写与病案管理问题时使用', which leaves trigger scope open-ended. It does not provide exclusion conditions or negative examples, so nearby medical-writing questions outside the intended source could be matched unintentionally.
Suspicious Unicode normalization or mixed-script content
This markdown file contains a natural-language requirement that medical record writing '应当使用中文' and only allows limited exceptions for abbreviations or terms without formal Chinese translations. Under the policy scope for all file types, this is a language/locale constraint that does not present user opt-in or explain a region-specific limitation within the skill file itself.
该 markdown 文件包含明确的自然语言要求“病历书写应当使用中文”，属于对语言使用的强制性约束。文件中未说明这是特定法规辖区、机构制度或经用户选择后的语言要求，因此符合需要标记的语言/locale policy violation 条件。
This markdown file presents all instructional content in Chinese and does not indicate that the user can choose another language or that the material is intentionally restricted to a Chinese-speaking audience. Under the policy for natural-language violations, forcing a specific language without opt-in can be a locale-policy issue.
Suspicious Unicode normalization or mixed-script content
L0114 states '性别指患者的社会性别', which is a natural-language policy choice embedded in a general medical documentation standard. The file does not indicate that this terminology is optional, jurisdiction-specific, or subject to user/institution choice, so it appears to impose a locale/policy preference without opt-in.
The text instructs providers to communicate using language the patient can understand, but the overall document is exclusively in Chinese and does not offer any language or locale choice for patients who may not read Chinese. For a consent-form template, this can create a language-policy issue because it presumes a fixed language without explicit opt-in or accommodation.
Suspicious Unicode normalization or mixed-script content
The text states that electronic medical records 'must use Chinese and medical terminology,' which is a natural-language locale constraint. Under the policy, forcing a specific language without user opt-in or clear documented justification is a reportable violation.
This section again requires use of Chinese for record writing, creating the same locale-policy issue in another part of the file. The document does not present this as an optional or user-selected language setting, nor explicitly justify it as a region-specific compliance constraint.
As a markdown file, this content is subject to natural-language policy review. The text states that '中医术语的使用应依据' specified Chinese standards and references, which imposes a fixed language/terminology regime without any user opt-in or alternative locale handling; this can conflict with a policy requiring language choice unless clearly justified in-file.
SQP-3 applies to all file types and covers language or locale policy violations in natural-language content. This markdown file presents all instructions and form content exclusively in Chinese without any user opt-in, alternative language, or explicit justification that the skill is intended only for a Chinese-language audience.
No suspicious patterns detected.
