Security audit
Security checks for vulnerabilities and agentic risk
This is a straightforward Chinese social-media writing helper with no code execution, credential access, persistence, or hidden data handling.
Install this if you want a drafting assistant for Chinese social media posts. Review generated claims, citations, banned-word checks, and CTAs before publishing, and be explicit about platform and language when asking for content.
The activation triggers are broad enough to match many ordinary writing-related requests, which can cause the skill to activate unexpectedly outside a clearly intended context. That increases the chance of prompt hijacking of normal user workflows, undesired behavior changes, or content generation in contexts where the user did not explicitly request this specific skill.
The description states the skill is for Chinese social media and the document consistently frames output around Chinese platforms and Chinese-language conventions, but it does not explicitly ask the user to confirm language preference. This can conflict with a language/locale choice policy when the skill is invoked from generic triggers rather than explicit Chinese-language requests.
No suspicious patterns detected.
