Security audit
Security checks for vulnerabilities and agentic risk
This is a content-advice skill with Chinese-language guidance and no code execution, persistence, credential access, or hidden data flow.
Install this if you want a Chinese-first MrBeast-style advisor for video concepts, titles, hooks, retention, and platform/budget tradeoffs. Set your preferred language explicitly if you do not want Chinese responses.
The skill sets a default contract of '输出语言：中文' without checking the user's language preference or obtaining opt-in. This can cause unexpected language switching, reduce usability, and in safety-critical or compliance-sensitive contexts could lead to misunderstanding of instructions or outputs, though it does not directly enable code execution or data exfiltration.
The interface metadata is written in Chinese and presents the skill as 'MrBeast 视角' with a Chinese-only short description, which implies a fixed language/locale experience. The policy requires not forcing a specific language unless the user is given a choice or the locale restriction is clearly documented and justified.
This markdown file uses Chinese throughout its instructional headings and bullet points, which effectively imposes a specific language on the user. The policy for natural-language issues flags language or locale constraints when the skill does not offer an explicit user choice or opt-in.
This markdown file contains user-facing instructional content in Chinese while the surrounding structure is in English, but it does not state that the skill is intended specifically for Chinese-speaking users or offer an alternative language. Under the policy, forcing a specific language without opt-in can be a natural-language policy violation.
Line L21 instructs that, in a Chinese-platform context, the approach should first translate the underlying logic before discussing presentation form. This imposes a specific language/locale framing in the skill guidance without indicating user choice or opt-in, which can conflict with language/locale flexibility policies.
No suspicious patterns detected.
