Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed WeChat article-writing helper with no code execution, persistence, credential access, or hidden system behavior, though users should review promotional content for disclosure and accuracy.
Installers should treat this as a specialized drafting aid for WeChat-style articles. For marketing or brand pieces, clearly disclose sponsorship or advertising relationships, verify factual and data claims, and avoid using it when the user only wanted generic writing help rather than a full WeChat Official Account article.
The skill’s activation cues are broad and overlap with ordinary writing and content-help requests, which can cause the agent to invoke this specialized behavior in contexts the user did not clearly intend. That increases the chance of unintended long-form content generation, prompt-scope confusion, and bypass of more appropriate general-purpose handling or safer domain-specific guidance.
The skill explicitly supports advertorials and brand-promotion content but provides no guidance on disclosure, transparency, or compliance obligations. This can facilitate generation of undisclosed sponsored content or misleading promotional material, creating legal, policy, and trust risks for users and audiences.
The document is explicitly framed as a WeChat Official Account article reference, which targets a specific platform and implied Chinese-language/content locale. The file does not offer any user choice or opt-in for language/locale, and the examples are tailored to that locale throughout.
No suspicious patterns detected.
