Security audit
Security checks for vulnerabilities and agentic risk
This is a markdown-only Chinese writing-style rewriting skill with no code execution, persistence, credential access, or hidden data movement, though its broad triggers could affect ordinary writing requests.
Install this only if you want Chinese draft or transcript rewriting in Antonia's personal style and you have appropriate rights or consent to use that style. Consider narrowing the trigger phrases so generic requests like writing an article or converting speech to prose do not automatically impose this specific voice.
The primary skill description is written as a Chinese-only writing-style cloner for producing articles in Antonia's style, and the README does not indicate that users may choose another language or locale. Under the stated policy, a skill that imposes a specific language without opt-in is a natural-language policy violation.
The trigger set includes generic phrases like '帮我写文章', '写成文章', and '口语转书面', which overlap heavily with common assistant tasks. In context, this is more dangerous because the skill contains a large, prescriptive persona/style payload; ambiguous routing could silently steer broad user requests into unauthorized imitation or content shaping not requested by the user.
The trigger keyword at line 6 is broad enough to match many ordinary writing requests, which can cause the skill to activate outside its intended niche. That creates prompt-scope hijacking risk: users asking for generic writing help may unknowingly invoke a style-cloning skill that imposes hidden behavioral instructions and unnecessary transformation of user content.
This markdown file establishes transformation rules exclusively in Chinese and directs use of a specific style profile, but does not indicate that the language choice is optional or limited to Chinese-language workflows. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation.
No suspicious patterns detected.
