Security audit
Security checks for vulnerabilities and agentic risk
This is a coherent Chinese-language AI short-drama production guide made of Markdown templates, with no code execution or hidden local access.
Install this as a content-production helper, not as a privacy-preserving local workflow. Be careful before pasting unpublished scripts, client material, voice samples, or personal data into recommended third-party AI tools, and confirm copyright and voice-cloning permissions for commercial use.
All user-facing examples and descriptions are presented only in Chinese, and the usage section implies interaction through Chinese-language prompts without mentioning alternative languages or user choice. This may constitute a language/locale policy issue if the skill is expected to support user preference rather than enforce a single language by default.
The README advertises very broad quoted trigger phrases such as general requests for writing scripts, making prompts, production advice, and monetization help. In an agentic environment, these ordinary-language examples can cause the skill to activate on routine conversation beyond the user's explicit intent, increasing the chance of unwanted prompt injection exposure, accidental tool use, or inappropriate content generation.
The activation logic is broad enough that ordinary user requests about making a short drama could automatically invoke this skill without an explicit opt-in or confirmation. That can cause unintended routing, reduce user control, and increase the chance the assistant ignores better-matched instructions or language preferences in multi-skill environments.
The workflow directs users to paste dialogue scripts into third-party voice providers such as ElevenLabs without disclosing that the script content will be transmitted to external services. If scripts contain unpublished story material, client work, personal data, or sensitive business information, this can cause unintended data exposure, retention, or secondary use by those providers.
The title explicitly presents the skill as an 'AI短剧 Prompt 模板库', and throughout the file the templates prescribe Chinese-specific outputs such as 'Young Chinese female', 'Chinese narrator', and 'Chinese short drama poster'. The file does not state that this is a region-specific skill or offer an opt-in or alternative language/locale, which is a natural-language locale policy concern.
The skill description, tags, and trigger phrases are entirely Chinese-language, which effectively constrains use to Chinese without stating that this is optional or region-specific. Because no opt-in or alternative language handling is described, this can be interpreted as a language-policy limitation embedded in the skill's natural-language interface.
This markdown file contains user-facing guidance exclusively in Chinese and does not provide an opt-in, alternative language, or justification for a Chinese-only audience. Under the policy rule for language/locale constraints, forcing a specific language without user choice is a natural-language policy issue.
The entire skill file is written in Chinese and presents its templates and instructions only in that language, with no indication that users may choose another language or locale. This can conflict with a language/locale policy requiring user choice or opt-in rather than a fixed language.
