Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only medical-device regulatory reference hub with no runtime authority, but its self-attestation and manifest/security claims should not be treated as independently verified.
Install only as a reference aid. Verify dates, classifications, fees, and submission requirements against current regulator sources before making compliance decisions, and do not rely on the package's missing attestation or stale manifest hashes as proof of integrity.
The entire agent instruction file is written in Chinese and does not offer a language choice or explain a required locale constraint. Under the policy rule, forcing a specific language without user opt-in can be a natural-language policy violation because maintainers or agents may be required to operate in a language they did not choose.
The skill declares itself as a prompt-only artifact with no runtime or filesystem capability, yet later claims that package files such as ATTESTATION.md, manifest.json, and security_results.json were read. This creates a provenance/integrity mismatch: users or upstream agents may trust security assertions that the skill cannot actually verify, enabling false assurance and misleading compliance decisions.
The trigger condition activates on very broad medical-device registration and compliance queries, which can cause the skill to load in situations beyond its narrowly intended scope. In a regulated domain, over-broad activation increases the chance the agent will present this hub as authoritative context for jurisdiction-specific or high-stakes compliance questions where narrower routing or explicit qualification is needed.
This markdown file contains all instructional content in Chinese, with some Japanese terminology, and does not indicate that the user can choose another language. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is clearly documented and justified.
The entire skill is written only in Chinese and provides no indication that users may choose another language or that the skill is intentionally limited to Chinese-speaking users. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern unless the locale restriction is explicitly documented and justified.
The table states the language requirement simply as '中文' for China, which is a natural-language locale constraint. In this skill file, that constraint is presented without an explicit opt-in mechanism or clear statement that the skill itself is limited to a China-specific compliance workflow, so it can be read as forcing a language requirement.
The display name is presented only in Chinese, which can create a locale-specific user experience without explicit opt-in. Under the policy, language constraints should either offer a choice or be clearly justified as region-specific; this file presents bilingual content elsewhere but does not state that the Chinese-only title is intentional or optional.
This manifest references numerous Chinese-titled markdown resources, which strongly suggests the skill is organized around a single language/locale. Because no opt-in, alternative language option, or justification is present in the manifest, this may conflict with the policy against forcing a specific language without user choice.
The skill file is entirely written in Chinese and presents itself as a general 'hub' for GMP quality-system guidance without offering any language choice or stating that it is intended only for Chinese-speaking users. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale constraint is explicitly documented and justified.
This markdown file presents all titles, descriptions, and usage instructions exclusively in Chinese. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale constraint is explicitly documented and justified.
文件标题和全文内容均以中文呈现，且未说明该技能仅面向中文用户，或提供其他语言/locale 的选择。按规则，若技能强制特定语言而无用户选择或明确合理限定，可构成自然语言层面的语言/locale 政策问题。
Line L167 states '审查资料（STED 基础，全日文）', which is a natural-language constraint forcing a specific language. Under the policy rule, language requirements should either offer user choice or be clearly documented and justified as region-specific; this line presents the requirement without that justification in the skill text.
SQP-3 applies to all file types and covers language or locale policy violations. This skill content appears to force a single language for all users, and the file does not provide an opt-in, alternative language option, or an explicit statement that the skill is limited to Chinese-speaking users only.
该技能文件全文以中文呈现，且未见说明该资料仅面向中文用户、特定地区注册场景，或允许用户选择其他语言。根据规则，若技能在自然语言层面强制特定语言而无用户选择或明确 justified scope，可构成语言/locale 政策问题。
This manifest-style JSON includes multiple natural-language field names in Chinese for score categories, but there is no indication that the skill supports language selection or that Chinese output is intentional and documented. For a general-purpose skill artifact, forcing a specific language can violate locale-choice policy when users are not given an opt-in or alternative.
No suspicious patterns detected.
