Security audit
Security checks for vulnerabilities and agentic risk
This is a simple copywriting prompt skill with no code, external access, persistence, or privileged behavior.
Installers should treat this as a low-risk content-writing skill. Confirm that Chinese-language instructions are acceptable for the intended users and that broad activation for copywriting requests matches how they want skills invoked.
The manifest description and all user-facing instructions are presented only in Chinese, with no indication that users may choose another language or locale. This creates a language-policy concern because the skill appears to assume a fixed language without user opt-in or documented justification.
The usage guidance says only to 'tell the AI the type and topic of copy you want created,' which is a very general activation description without explicit trigger phrases, scope limits, or negative examples. This broad wording overlaps with ordinary conversation about writing assistance and could cause unintended invocation of the skill.
No suspicious patterns detected.
