Security audit
Security checks for vulnerabilities and agentic risk
This is a prompt-only Chinese short-video planning skill with no evidence of hidden execution, data access, persistence, or automatic posting.
Installers should understand this skill is aimed at Chinese short-video platform workflows and produces planning guidance rather than verified legal, copyright, or platform-policy clearance. Review any generated marketing and compliance claims before publishing.
This file contains user-facing natural-language content exclusively in Chinese, including the description, parameter descriptions, workflow, and output template. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly justified, which is not present here.
The schema and metadata are entirely Chinese-oriented and do not provide a language-selection parameter or justify a locale restriction. This can cause the agent to override user language expectations, misunderstand prompts, or generate content in an unintended language, which becomes more risky in a multi-platform publishing workflow where incorrect language output may lead to user confusion, reputational harm, or accidental posting errors.
This markdown file contains substantive user-facing content in Chinese, but it does not state that the skill is intended for Chinese-speaking users or offer any language/locale choice. Under the policy rule for natural-language violations, forcing a specific language without opt-in can be a policy concern.
The natural-language documentation forces a specific language for all users of the skill. Under the policy, language constraints should either be optional for the user or explicitly justified as region-specific.
The skill description is very broad and promises an end-to-end content pipeline without defining clear boundaries, exclusions, or triggering conditions. In an agent setting, overbroad scope can cause the skill to activate for loosely related requests and produce actions or guidance beyond the user's intended context, increasing the chance of misuse or unsafe automation.
No suspicious patterns detected.
