Security audit
Security checks for vulnerabilities and agentic risk
This is a Chinese legal-exam study helper that processes user-provided materials to generate practice questions, with no evidence of hidden execution, exfiltration, or privilege abuse.
Before installing, confirm that the save directory is changed to your own workspace and avoid uploading client-confidential, personal, or copyrighted legal materials unless you are comfortable having them transcribed, OCR-processed, and analyzed for question generation.
The trigger phrases include very broad terms such as '法考' and '练习题', which can appear in ordinary conversation and may cause the skill to activate outside the user's intended scope. This can lead to unintended processing of uploaded materials or legal-study content, increasing privacy risk and confusing skill routing.
The skill explicitly processes uploaded videos, documents, and images through transcription, OCR, and content extraction, but it does not warn users that their data will be transformed and analyzed. In a legal-study context, uploaded materials may contain personal notes, copyrighted course content, or sensitive case-related information, so silent processing creates meaningful privacy and consent risk.
All user-facing instructions and trigger phrases are presented only in Chinese, and the skill is framed around Chinese legal exam preparation without explicitly stating that it is intentionally Chinese-only or offering any language choice. Under the policy, forcing a specific language without user opt-in can be a natural-language policy issue unless the locale constraint is clearly documented and justified.
This markdown file is entirely Chinese-language content, including headings, descriptions, and recommendations, with no indication that users may choose another language or that the resource is intended only for a Chinese-speaking audience. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation.
No suspicious patterns detected.
