Security audit
Security checks for vulnerabilities and agentic risk
This is a simple Chinese-language demo skill that replies with basic runtime information and does not request sensitive access or persistence.
Install this as a demo or learning skill. Be aware it replies in Chinese and may display your workspace path in the chat when run.
The instruction to invoke the skill by merely mentioning its name is overly broad and can lead to unintended activation in normal conversation. In agent ecosystems where skill routing may rely on keyword or name matching, this increases the chance of accidental execution and unexpected behavior, even though the documented skill appears to be a harmless demo.
The user-facing documentation is entirely in Chinese, which implies a fixed language choice without stating that users can select another language or that the skill is intentionally region-specific. This can violate language or locale policy when no opt-in or justification is provided.
This code file contains user-facing natural-language strings and documentation primarily in Chinese, including replies sent to the user and metadata descriptions. Under the policy rule for language/locale, forcing a specific language without offering user choice can be a natural-language policy violation.
The manifest description is written only in Chinese, which can indicate a language-specific constraint without any accompanying opt-in, alternative locale, or justification that the skill is region-specific. Under the policy criteria, forcing a specific language without user choice can be a natural-language policy violation.
No suspicious patterns detected.
