universal-data-analyst

基于数据本体论自动识别数据类型，生成分析方案及脚本，输出数据质量报告和多格式智能分析报告，支持多种数据格式。

Before installing or running this skill, consider the following: - Do not enable fully autonomous execution unless you trust the environment and have strict sandboxing (e.g., no outbound network, limited filesystem rights, isolated VM/container). - The skill generates Python scripts from LLM output and can execute them. Always review generated scripts manually (use the step-by-step mode) before executing, especially if the data is sensitive or the runtime has network/database access. - The package doesn’t declare required LLM API keys or DB creds, but its examples expect you to use external LLMs or DB connection strings — treat those credentials as sensitive. Provide them only in controlled ways and prefer ephemeral/separated accounts. - If you need to run this in production, run it in a sandbox with egress blocked or restricted, and use least-privilege credentials for any database connections. - Note the claimed "no hardcoding / always LLM-driven" promise is not strictly true: the code includes heuristics and defaults. Expect hybrid LLM+heuristic behavior. - If possible, run the code audit (search for subprocess, os.system, exec, open(..., 'w'), network libraries) and add explicit guardrails (denylist network calls, require signed/approved scripts) before enabling autonomous use.

Type: OpenClaw Skill Name: universal-data-analyst Version: 1.0.3 The skill bundle implements a comprehensive data analysis workflow that includes high-risk capabilities, specifically the execution of LLM-generated Python scripts using `subprocess.run` in `orchestrator.py` and the ability to connect to arbitrary SQL databases via `layers/data_loader.py`. While these features are aligned with the stated purpose of automated data analysis, they represent a significant security risk for Remote Code Execution (RCE) if the LLM is manipulated via prompt injection or if malicious inputs are provided. No evidence of intentional malice, such as hardcoded exfiltration endpoints or unauthorized file access, was found in the code logic.