Excel AI Analyzer

Automatically analyze Excel data files to generate statistical summaries, detect anomalies, create visual charts, and provide analysis reports and suggestions.

Security Scan

The skill mostly implements offline Excel analysis, but there are internal inconsistencies (declared charting capability/dependency not implemented) and a prompt-injection signal in SKILL.md — review before installing or run in a sandbox.

Purpose & Capability

The skill's stated purpose (read Excel, stats, anomalies, charts, Markdown reports) mostly matches the code: index.js reads Excel, computes statistics, detects anomalies, and emits a Markdown report. However SKILL.md/README advertise chart generation and list chartjs-node-canvas as a dependency while package.json and index.js contain no chart-generation code or that dependency. This is an incoherence (possible unfinished feature or inaccurate docs).

Instruction Scope

Runtime instructions are scoped to 'upload / provide Excel file' and do not request unrelated files or credentials. However the SKILL.md contains detected unicode-control-chars (prompt-injection signal). Hidden control characters in documentation can be used to smuggle instructions into an agent context — this warrants manual inspection of SKILL.md for invisible characters before trusting the skill.

Install Mechanism

No explicit install spec is provided (instruction-only install). The package uses only the well-known npm dependency 'xlsx' (package.json/package-lock.json). There are no downloads from arbitrary URLs or archive extraction. package-lock references an npm mirror (registry.npmmirror.com), which is expected for npm distributed packages but worth noting if your environment restricts registries.

Credentials

The skill does not request environment variables, credentials, or config paths. The code performs only local file I/O on the provided Excel file. This level of access is proportionate to the claimed functionality.

Persistence & Privilege

always is false and the skill is user-invocable; it does not request persistent/agent-wide privileges or modify other skills. No elevated persistence or automatic always-on behavior detected.

Scan Findings in Context

[unicode-control-chars] unexpected: Hidden/unicode control characters were found in SKILL.md. This is not expected for an Excel analysis skill's documentation and can be used for prompt-injection manipulation of an agent. Manual inspection and removal of invisible characters is recommended.

What to consider before installing

What to consider before installing: - The code performs local analysis only (reads an Excel file, computes stats, detects anomalies, writes a Markdown report). That matches the core description. - The docs advertise chart generation and a chartjs-node-canvas dependency, but neither package.json nor index.js implements charting — the feature appears missing or the docs are out of date. If you need charts, ask the author or inspect/extend the code before relying on it. - SKILL.md contains hidden unicode control characters (prompt-injection signal). Inspect the SKILL.md file in a text editor that can reveal invisible characters; remove them or request a clean copy from the author. - There are no requested credentials or network calls in the code, which limits exfiltration risk, but still run npm install and tests in an isolated sandbox (or CI) before adding to a production agent. - If you plan to use this on sensitive spreadsheets, run it in an isolated environment and review/modify the code to ensure it meets your security and feature requirements. If you need high confidence that nothing external is contacted, search the codebase for network APIs (http/https, child_process, net, fetch) — current files show none.

智能 Excel 数据分析技能 - 自动分析数据、生成统计报告、创建可视化图表。

功能

• 📊 自动数据分析：读取 Excel 文件，自动识别数据类型和结构
• 📈 统计分析：计算均值、中位数、标准差、趋势分析
• 🔍 异常检测：识别数据中的异常值和离群点
• 📝 报告输出：生成 Markdown 格式的分析报告
• 💡 智能建议：基于数据特征给出分析建议

使用方式

帮我分析这个 Excel 文件
上传：data.xlsx

或

分析 /path/to/file.xlsx 的销售数据

输出示例

• 数据概览（行数、列数、数据类型）
• 统计摘要（均值、最大/最小值、分布）
• 趋势分析（时间序列数据）
• 异常值标记
• 可视化图表
• 分析结论和建议

依赖

• xlsx (Excel 文件解析)
• chartjs-node-canvas (图表生成)
• markdown 生成

作者

倒里牢数 · 严谨专业版

版本

1.0.0