Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed prompt-building guide for Douyin cover images and does not show hidden execution, persistence, credential access, or destructive behavior.
Before installing, consider that the workflow is mainly documented in Chinese and may encourage uploading a portrait to an image model; only use photos you are comfortable providing to the chosen image-generation service.
The description states the skill is for Chinese creators and the rest of the instructions are written entirely in Chinese, which effectively constrains use to a specific language/locale. There is no opt-in, alternative language option, or explicit justification that this is a region-specific compliance or localization requirement.
The heading is written entirely in Chinese and frames the guidance as the required implementation approach, with no indication that users may choose another language or locale. This can violate language/locale policy when a skill implicitly forces a specific language without user opt-in.
This file’s natural-language content is fully Chinese, including the title and all update notes, with no indication that users may choose another language. Under the policy rule, forcing a specific language without opt-in can be a natural-language policy concern unless the locale restriction is explicitly justified.
The README states that the skill is 'for Chinese creators' in both Chinese and English, which presents a locale-targeting constraint in natural language. Because the file does not clarify that this is an optional audience focus or provide an explicit language/locale choice, it can be interpreted as a policy-relevant locale restriction.
The usage instructions, examples, and operational guidance are presented only in Chinese, which can amount to a language/locale policy issue when no user opt-in or alternative language is offered. The documented behavior does not indicate that the skill is region-specific or that users can choose another language.
No suspicious patterns detected.
