Security audit
Security checks for vulnerabilities and agentic risk
This skill is a narrow Chinese thesis-introduction drafting helper with no executable code, persistence, credential access, or hidden data flow.
Install only if you want help drafting Chinese thesis introduction sections. Provide your topic, method, school format, and citation requirements, and verify any generated academic claims or citation placeholders before submitting work.
The manifest description specifies writing detailed Chinese introduction chapters or sections, but does not mention any option for users to request another language. Because this is natural-language behavior embedded in the skill definition, it can constitute a language-policy violation.
The instruction says the skill should be used only to write the introduction part of a Chinese academic paper and that the default output is a polished Chinese section. This imposes a specific language behavior without indicating that the user may choose another language or explicitly opt in, which matches the locale/language policy concern.
The skill metadata and default prompt hard-code Chinese output without indicating that this is conditional on user preference. If invoked for users expecting another language, the system may produce unusable output, override user intent, or create confusion that degrades reliability and trust in the agent's behavior.
The default invocation prompt is very broad and can trigger the skill whenever a user asks for thesis-writing help, without clearly limiting use to introduction-only tasks. This increases the chance of overbroad routing, causing the agent to apply the skill in unintended contexts and potentially generate inappropriate or misleading academic content outside its stated scope.
The guide explicitly instructs the skill to produce a full Chinese introduction format by default, which can override a user's preferred language if the system does not separately enforce user choice. This is not a code-execution or data-exfiltration issue, but it can cause unwanted behavior, reduce usability, and create prompt-level policy noncompliance when users request another language.
No suspicious patterns detected.
