Security audit
Security checks for vulnerabilities and agentic risk
This is a text-only Chinese RAG knowledge-curation skill that asks the agent to clean, chunk, tag, and score user-provided documents without adding hidden execution, network, credential, or persistence behavior.
Installers should be comfortable with Chinese-language instructions and should review any generated recommendations before connecting them to a real vector database pipeline, especially when source documents contain sensitive enterprise material.
The README presents all user-facing instructions and descriptions in Chinese only, which can constitute a language/locale policy violation when no user opt-in or alternative language option is provided. The file does not indicate that the skill is intentionally limited to Chinese-speaking users or a China-specific compliance context.
The manifest description and the entire user-facing skill content are presented exclusively in Chinese. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly documented and justified, which is not present here.
The manifest text for the skill description and parameter descriptions is entirely in Chinese, with no indication that language selection is optional or that the skill is specifically scoped to Chinese-speaking users. This can violate a language/locale policy when a skill implicitly forces one language without user opt-in or documented regional justification.
No suspicious patterns detected.
