Security audit
Security checks for vulnerabilities and agentic risk
This is a Chinese-language video script generation skill with no code execution, credential handling, persistence, or hidden data access.
Install this if you want Chinese-language help drafting AI video scripts and shot plans. Be aware that broad trigger words such as video script, storyboard, and AI video may activate it for adjacent requests, and non-Chinese users may need to explicitly ask for another language.
The skill metadata advertises broad trigger terms such as '视频脚本', '分镜', and 'AI视频' without any documented activation boundaries, making accidental invocation more likely when users discuss adjacent topics. This is primarily a safety and routing issue rather than a direct exploit, but it can cause the wrong skill to activate and shape outputs unexpectedly.
The skill is written entirely in Chinese and presents Chinese-language behavior as the default without offering user language selection or stating a justified locale restriction. This can cause user-intent mismatches, reduce transparency, and lead to confusing or inaccessible outputs for non-Chinese users, though it does not create a strong direct security compromise in this content-generation context.
The trigger phrases are very broad and include common terms like '视频脚本', '分镜', and 'AI视频', which can cause the skill to activate for many ordinary user requests unrelated to this specific tool. Over-broad activation can hijack normal conversations, route users into unintended behavior, and reduce user control over when the skill is invoked.
The description is written to enforce Chinese-language behavior for outputs without any indication that the user can choose another language. This can override user preference, create confusing interactions, and make the skill behave unexpectedly in multilingual contexts.
No suspicious patterns detected.
