Security audit
Security checks for vulnerabilities and agentic risk
This markdown-only skill analyzes Vue component relationships and does not show hidden execution, persistence, network use, or credential handling.
Install this if you want a Vue project component map. Be aware it works by reading project source files recursively, so use it only on repositories you are comfortable having the agent inspect, and ask explicitly for your preferred output language if needed.
The skill description is broad enough that an agent may invoke it in loosely related situations, causing unnecessary recursive file analysis of a project. While this is not direct code execution, overbroad triggering can expand data exposure and increase the chance the agent reads more repository content than the user intended.
Forcing Chinese output without documenting language selection rules can cause the agent to ignore the user's preferred language or system locale, which is a policy/control weakness. This is mainly a usability and instruction-governance issue, but it can also reduce transparency if security-relevant analysis is emitted in an unexpected language.
This markdown file presents the entire skill guidance in Chinese, including headings, instructions, and examples, with no indication that the user can choose another language. The policy requires flagging language or locale constraints when a skill forces a specific language without user opt-in or documented justification.
This file presents all user-facing instructional content in a single language, which can constitute a language/locale policy issue when no opt-in or alternative is provided. There is no indication that the skill is intentionally limited to a Chinese-speaking or region-specific audience.
No suspicious patterns detected.
