Security audit
Security checks for vulnerabilities and agentic risk
The skill is a coherent Chinese-language A-share simulated trading decision workflow with disclosed report writing and guarded simulated order execution.
Install only if you want a Chinese-language A-share simulated strategy workflow. Expect it to read its bundled reference files, call market-data and simulated-trading tools when relevant, save decision reports under ./report/strategy, and generate chart SVGs when requested; it should not be used for real-money trading execution.
该代码块的核心目的与声明明显不符。声明描述的是一个交易决策/分析技能，应围绕首板赚钱效应、候选筛选、隔夜留仓判断和退出计划生成展开；但实际代码仅实现了市场数据可视化：从JSON读取K线数据，计算若干常见技术指标（SMA、EMA衍生的MACD、RSI），并生成SVG图表。它没有任何首板识别逻辑、A股首板候选筛选规则、赚钱效应统计、证据汇总、买卖建议分类、风险控制或T+1退出方案生成。因此这是主用途层面的实质性不匹配，而不是正常的辅助实现细节。
The skill clearly instructs reading multiple local reference files and writing a report into the user's workspace, but it declares no explicit tool scope or permissions boundary. That creates an authorization ambiguity: an orchestrator may grant broader file capabilities than users expect, increasing the chance of unintended file access or writes.
The manifest description is written as a Chinese-only invocation and behavior description, and the file provides no indication that users may choose another language. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern.
The skill instructs automatic creation of a report file in the user's workspace, including auto-creating directories, without any explicit warning or consent step. Silent filesystem writes can surprise users, overwrite expected artifacts, or be abused to persist unwanted content, especially when paired with undeclared file-write capability.
This markdown file presents the operational instructions entirely in Chinese, starting with the section headings and continuing through all guidance. Under the policy criteria, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly justified, which is not present here.
This markdown file contains all operational policy and decision instructions exclusively in Chinese, and there is no indication that users may choose another language or that the skill is intentionally restricted to a Chinese-speaking or region-specific audience. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.
The file’s operational instructions are written entirely in Chinese, beginning with the section header at L03, with no indication that language selection is optional or constrained by a documented regional requirement. This can violate language/locale policy because it effectively forces a specific language for users or downstream agents without opt-in.
The skill content is written entirely in Chinese, including core policy and operational instructions, with no indication that users can choose another language or that the skill is intentionally limited to a Chinese-speaking or region-specific context. This creates a natural-language policy concern because it effectively imposes a language requirement without explicit opt-in or justification.
This markdown file contains all operational policy instructions in Chinese, and there is no indication that users may choose another language or that the skill is intentionally limited to Chinese-speaking users. Per the policy, forcing a specific language without user opt-in is a natural-language policy violation.
This markdown file contains natural-language instructions exclusively in Chinese, and there is no indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking or region-specific audience. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation.
The template title, headings, labels, and body text are entirely in Chinese, which imposes a specific language on generated reports. The policy allows locale or language constraints only when the user is given a choice or when the constraint is clearly documented and justified; neither is present in this file.
L13-L15 position the skill as a strategy decision layer but also direct sim-trade to execute and keep records, and require the skill to independently acquire and verify raw market data. The manifest description in L03 emphasizes strategy evaluation and decision generation, not orchestration of trade execution and evidence acquisition workflows.
The manifest description in L03 frames the skill as evaluating market conditions, screening candidates, and generating BUY/WATCH/NO_TRADE decisions with evidence. However, L54 mandates persisting a standardized report to ./report/strategy/... and creating directories if needed, which goes beyond pure decision generation into filesystem write behavior not reflected in the manifest description.
The schema headings and instructions from L03 onward are written in Chinese, which effectively imposes a specific language for users of this skill reference. The file does not provide an opt-in, alternative language, or a documented justification that the schema is intended only for a Chinese-language or region-specific workflow.
