Security audit
Security checks for vulnerabilities and agentic risk
This skill is a simple Chinese ecommerce copy generator with no evidence of hidden access, persistence, network activity, or destructive behavior.
Install this if you want Chinese-language ecommerce/social copy generation. Review output for truthfulness and platform compliance before publishing, since the skill can produce persuasive marketing language from limited product details.
The trigger examples are very broad and lack any constraints on required inputs, allowed scope, or exclusions. This can cause the skill to activate unexpectedly on generic user phrases and perform content generation in unintended contexts, increasing the chance of misuse, prompt confusion, or overbroad invocation in workflows handling sensitive product or marketing data.
This code generates user-facing output entirely in Chinese, including platform labels, templates, hooks, and recommendation text. The file does not offer any language selection or explain a region-specific constraint, which creates a natural-language locale policy violation under the requirement to avoid forcing a specific language without user opt-in.
The natural-language instructions and examples are entirely in Chinese, which can amount to forcing a specific language for interaction if no opt-in or alternative is provided. The file does not explain that the skill is intentionally limited to a Chinese-language or region-specific audience.
The comment says the method batch-generates content for multiple platforms, but the surrounding template definitions only cover 小红书、抖音、朋友圈 while the implementation also generates 知乎 content in generateAll(). With no manifest available this is not a manifest mismatch, but the inline documentation and earlier code structure suggest a narrower supported-platform set than the code actually implements.
No suspicious patterns detected.
