Security audit
Security checks for vulnerabilities and agentic risk
This is a prompt-and-image helper for Chinese social media quote cards, with no evidence of hidden execution, persistence, credential access, or data exfiltration.
Installers should understand this skill is primarily Chinese-language and focused on image prompts for quote-card/social-media art. Review generated image prompts for age-appropriate character descriptions and preferred language/style before sending them to an image model.
The skill metadata and all user-facing instructions are written to operate in Chinese, and the examples assume Chinese inputs and outputs, but the file does not state that this is optional or limited to a Chinese-only context. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern.
The trigger field includes broad descriptive phrases such as “情绪插画” and “金句卡片” that are not tightly scoped to a unique invocation pattern. This can cause accidental activation in unrelated conversations, increasing the chance that the skill runs when the user did not intend it and influencing outputs or tool use unexpectedly.
The prompt includes fixed Chinese text ("人生没有 Ctrl + Z，但代码可以。") as part of the required output, which imposes a specific language choice. There is no indication that the user can opt into another language or that the Chinese-only wording is required for a documented region-specific purpose.
This plain-text skill content presents its title and primary user-facing text only in Chinese, with no indication that language selection is optional or that the skill is specifically limited to a Chinese-speaking context. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern.
No suspicious patterns detected.
