360 Secure SkillHub
360 安全技能中心

Moark Text Moderations

该 Skill 通过捆绑的 Python 脚本调用 Gitee AI 文本审核接口,对用户指定的文本进行违规或冒犯性内容审查,从脚本输出中提取以 MODERATION_RESULT: 开头的行,以 Markdown 展示审核结果并附简要说明;需安装 openai 依赖并提供 API Key。

fchange
fchange
热度 53.56
最近更新 2026-05-11 17:35:51
分类:安全依赖:代码执行 / 第三方 API / 内部调用大模型应用场景:API 集成 / 数据处理

安装技能

复制下面的话术发给你的 Agent,它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill: npx secure-skills-cli add moark-text-moderations
Metadata
name
moark-text-moderations
description
Perform text review on user-specified input text that may be inappropriate or offensive.
metadata
{"openclaw":{"emoji":"🛡️","requires":{"env":["GITEEAI_API_KEY"]},"primaryEnv":"GITEEAI_API_KEY"}}

Text Moderation

This skill allows users to perform text review on user-specified input text that may be inappropriate or offensive using an external GITEE AI API.

Usage

Ensure you have installed the required dependencies (pip install openai). Use the bundled script to perform text moderation.

python {baseDir}/scripts/perform_text_moderation.py --text "User-specified input text" --api-key YOUR_API_KEY

Options

No additional parameters are required for this skill.

Workflow

  1. Execute the perform_text_moderation.py script with the parameters from the user.
  2. Parse the script output and find the line starting with MODERATION_RESULT:.
  3. Extract the moderation result from that line (format: MODERATION_RESULT: ...).
  4. Display the moderation result to the user using markdown syntax: 🛡️[Moderation Result]

Notes

  • If GITEEAI_API_KEY is none, you should remind user to provide --api-key argument
  • You should not only return the moderation result but also provide a brief summary of the moderation result based on the user's input text.
  • When you add prompt, you should honestly repeat the requirements from user without any additional imaginations.
  • The script prints MODERATION_RESULT: in the output - extract this result and display it using markdown image syntax:🛡️[Moderation Result].
  • Always look for the line starting with MODERATION_RESULT: in the script output.