Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only research skill for public creator and one-person-business case studies, with a clearly disclosed Chinese-output default but no hidden execution, persistence, or credential access.
Install this if you want Chinese-language public case-research workflows and reusable evidence templates. Before using it on a person or brand, keep the work limited to public sources and explicitly request a different output language if Chinese is not what you want.
The manifest-style description says the skill produces Chinese outputs, creating a fixed language expectation. Because no alternative language option or opt-in mechanism is described there, this is a natural-language policy violation under the language/locale rule.
The markdown repeatedly instructs the skill to default to Chinese output, which is a language/locale constraint expressed in natural language. The file does not present this as an explicit user choice or opt-in, so it conflicts with the policy requirement to avoid forcing a specific language without user consent.
The default prompt hard-codes that research output should be produced in Chinese, which overrides normal user language preference unless the caller explicitly counter-instructs it. This is primarily a policy and usability risk rather than a direct security exploit, but it can cause unwanted behavior, reduce transparency for users who cannot review the output, and weaken user control over agent responses.
This markdown template is entirely written in Chinese, beginning with the title at L001 and continuing through all section headings. Because the file provides no indication that language choice is optional or region-specific, it can be read as enforcing a specific language/locale without user opt-in.
