Security audit
Security checks for vulnerabilities and agentic risk
This is a Chinese-language PRD writing helper made of Markdown templates, with no evidence of hidden execution, persistence, credential use, or data exfiltration.
Install this if you want a Chinese PRD drafting template skill. Be aware that it may activate on broad PRD-related phrases and generated example PRDs may mention third-party integrations that still need normal privacy, consent, and token-handling review before implementation.
The README lists trigger phrases such as "产品需求文档" and "帮我写PRD" without clarifying when the skill should or should not activate. These phrases are broad enough to overlap with ordinary conversation about PRDs, and the file provides no negative examples or scope constraints to reduce accidental matches.
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
- **版本**: 2.0.0
- **作者**: AI Assistant
- **标签**: product, prd, documentation, ai, auto-write
## 文件结构
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
- **版本**: 2.0.0
- **作者**: AI Assistant
- **标签**: product, prd, documentation, ai, auto-write
## 文件结构
The description presents the skill entirely in Chinese and states it will generate PRD documents directly, implying a fixed language/locale behavior. There is no indication that users may choose another language, which can violate language/locale policy when no opt-in is provided.
The example PRD explicitly includes external stock data sources and notification channels such as Feishu bots and email, but does not warn that user inputs, stock preferences, contact endpoints, and alert metadata may be transmitted to third-party services. This omission can lead downstream users or implementers to design and deploy the feature without adequate notice, consent, or privacy controls, increasing the risk of unintended data disclosure and compliance issues.
The manifest explicitly sets the skill language to "zh-CN" and the surrounding content is entirely Chinese, which indicates a fixed language/locale constraint. Under the policy, forcing a specific language without offering user choice or documenting a justified region-specific need is a natural-language policy violation.
The entire PRD template is written in Chinese, including headings, field labels, and placeholder guidance, which effectively mandates a specific language for skill users. The file does not offer a language/locale choice or explain that the template is intended only for a China-specific or Chinese-speaking context.
This markdown template is entirely written in Chinese, including headings, field labels, and instructional placeholders, which implicitly constrains generated PRDs to a specific language. The file does not offer an alternative language option or state that the template is intended only for a Chinese-speaking or region-specific context.
The natural-language instructions and trigger phrases are entirely Chinese, and the README does not state that the skill is region-specific or that users may choose another language. Under the language/locale policy, forcing a specific language without opt-in can be a policy concern.
No suspicious patterns detected.