MySQL Database CLI Skill

MySQL 数据库操作技能。通过 mysql CLI 连接数据库，执行 SELECT 查询、INSERT/UPDATE/DELETE 增删改、批量 SQL 执行、事务控制、数据库/表管理、JSON 格式输出。适用场景：查用户数据、统计报表、数据导入导出、数据库巡检、表结构查看、远程连接、生产环境调试。触发关键词：...

This appears to be a legitimate MySQL CLI instruction guide, but it is sloppy in ways that matter for safety. Before installing or using it: (1) Confirm the skill author/source — there is no homepage or publisher info. (2) Expect to provide database credentials to actually use these commands; the SKILL.md shows MYSQL_PWD and ~/.my.cnf but the skill metadata doesn't declare required env vars — verify how you'll supply secrets and avoid exposing passwords in process env when possible. (3) Review and restrict what the agent is allowed to run: the examples include destructive operations (DELETE, UPDATE), file-writing on the DB server (INTO OUTFILE), and file import (LOAD DATA LOCAL INFILE). Only allow the skill to run against safe/test databases unless you fully trust the user and environment. (4) Ask the publisher to: declare required binaries (mysql, jq, sed), list expected env vars/credential names, remove root/cleartext-password examples, and fix shell redirection examples (use /dev/null for POSIX shells). If you cannot verify the source or do not want the agent to have autonomous access to run high-impact DB commands, do not enable autonomous invocation or avoid installing the skill.

Type: OpenClaw Skill Name: mysql-database-skill Version: 1.0.1 The mysql-database-skill bundle is a well-documented set of instructions for an AI agent to interact with MySQL databases using the standard CLI. It provides comprehensive examples for querying, data manipulation, and schema management, while correctly advising on security practices such as using environment variables (MYSQL_PWD) or configuration files (~/.my.cnf) instead of plaintext passwords in command arguments. No evidence of data exfiltration, malicious execution, or prompt injection was found in SKILL.md or _meta.json.