Security audit
Security checks for vulnerabilities and agentic risk
This is a simple data-analysis prompt skill with broad Chinese trigger text and noisy reference notes, but no executable code or hidden high-impact behavior.
Before installing, consider whether you want a Chinese-language data-analysis helper that may activate on general data or spreadsheet requests. Review uploaded data normally, but this artifact does not add executable code, persistence, credential access, or hidden system changes.
The user-facing description and trigger examples are written only in Chinese, while no language-selection or opt-in behavior is documented. This can violate language/locale policy when a skill implicitly constrains interaction to a specific language without clearly offering alternatives or explaining why the locale is required.
The trigger phrases are broad everyday terms like '分析数据', '统计一下', and references to CSV/Excel uploads, which can cause the skill to activate during ordinary conversation rather than only when explicitly intended. In an agent system, overbroad activation increases the chance of unintended context capture, incorrect tool routing, and execution of a low-quality auto-generated skill on unrelated user input.
No suspicious patterns detected.
