Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

Multi Platform Publisher Agent

v1.0.0

多平台发布智能体。当需要在各平台发布书籍、管理发布计划、处理封面和格式时触发本技能。用于:(1) 将小说内容发布到Amazon KDP/番茄/起点/晋江等平台 (2) 适配各平台格式和封面要求 (3) 管理定时发布和更新节奏 (4) 处理滑块验证码 (5) 记录发布状态和回传数据

0· 88·0 current·0 all-time

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for ouyang198000/multi-platform-publisher-agent.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Multi Platform Publisher Agent" (ouyang198000/multi-platform-publisher-agent) from ClawHub.
Skill page: https://clawhub.ai/ouyang198000/multi-platform-publisher-agent
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install multi-platform-publisher-agent

ClawHub CLI

Package manager switcher

npx clawhub@latest install multi-platform-publisher-agent
Security Scan
VirusTotalVirusTotal
Suspicious
View report →
OpenClawOpenClaw
Suspicious
medium confidence
!
Purpose & Capability
The SKILL.md describes actions that legitimately require platform credentials, automation toolkits (Playwright, PyAutoGUI, UiPath), and third‑party captcha solver API keys. The registry metadata declares none of these as required binaries, env vars, or install steps — a mismatch between claimed capability and requested resources.
!
Instruction Scope
Instructions tell the agent to log into publisher platforms, perform web and desktop automation, call captcha‑solving services, and return platform IDs/status. The document does not specify how credentials are supplied/secured, where returned data is sent/stored, or any constraints on transmitting sensitive data — leaving room for credential use/exfiltration.
Install Mechanism
This is an instruction‑only skill (no install spec, no code). That limits on‑disk installation risk, but also creates an operational inconsistency: the SKILL.md explicitly depends on several libraries/tools and external services but provides no installation or runtime dependency declarations.
!
Credentials
The workflow clearly requires access to platform accounts and likely API keys for captcha services and possibly RPA licenses. Yet requires.env and primary credential fields are empty. Missing declared credentials is disproportionate and obscures what secrets the skill will need or access.
Persistence & Privilege
always:false and no install actions are declared. The skill does not request forced persistence in the manifest. Autonomous invocation is allowed by default but is not combined here with declared broad credential access in the manifest (though the SKILL.md implies such needs).
What to consider before installing
Before installing or enabling this skill, ask the publisher/author for the following clarifications: (1) Which exact binaries and libraries must be present (Playwright, PyAutoGUI, UiPath, etc.) and who installs them? (2) Exactly which environment variables or credential stores will be used for platform logins and captcha API keys, and how are those secrets supplied and protected? (3) Where does the skill send its "回传" data (internal system, external endpoint, who can read it)? (4) Which captcha‑solving vendor(s) will be used and do you have legal/ToS approval to use them for each platform? (5) Provide an explicit installation spec and a minimal permission/security checklist (network endpoints, logs, and storage locations). If you cannot get concrete answers and a manifest update that declares required credentials and install steps, avoid enabling this skill or run it in a tightly sandboxed environment with limited network/credential access and human approval before any platform login or publish action.

Like a lobster shell, security has layers — review code before you run it.

latestvk970pjj8c4t7cfzazttbg00wsd8436zn
88downloads
0stars
1versions
Updated 3w ago
v1.0.0
MIT-0

多平台发布师 · SKILL.md

角色定位

作为总管智能体「摸鱼宇哥」的下游,多平台发布师负责将小说创作师的成果高效、合规地发布到各平台,建立变现出口。

核心功能

1. 平台账号管理

支持平台:

平台发布方式变现模式优先级
Amazon KDP网页+API付费分成+KU🔴 高
番茄小说网页+APP广告分成🔴 高
起点中文网作家助手(桌面)付费订阅🟡 中
晋江文学城网页+桌面付费订阅🟡 中
Royal Road网页免费+打赏🟡 中
七猫小说网页保底分成🟡 中

账号配置:

platforms:
  amazon_kdp:
    email: xxx@xxx.com
    marketplace: com/legal
    kdp_select: true
  番茄小说:
    author_id: xxxxxx
    pen_name: xxx

2. 内容格式适配

格式转换规则:

平台格式要求敏感词处理封面尺寸
Amazon KDPDoc/TXT/ePub英文敏感词库2560×1600
番茄小说TXT/Word中文敏感词库512×768
起点中文网XML/Word起点敏感词库480×640
晋江TXT晋江敏感词库500×700

格式适配流程:

1. 接收Markdown源文件
2. 转换为目标平台格式
3. 执行敏感词替换
4. 生成封面图(AI生成+尺寸适配)
5. 生成书籍信息(书名/简介/标签)

3. 发布执行(合法自动化)

技术栈:

组件工具说明
浏览器自动化Playwright(标准模式)网页端发布
桌面自动化PyAutoGUI+uiautomation桌面程序操作
RPAUiPath/影刀复杂流程自动化
验证码第三方打码API滑块验证处理
调度APScheduler定时发布任务

发布流程:

1. 登录平台
2. 创建新书(填写书籍信息)
3. 上传封面
4. 设置标签/分类
5. 提交审核
6. 审核通过后设置发布计划
7. 执行定时发布

4. 滑块验证码处理

处理原则:

  • 使用合法第三方打码服务
  • 不尝试破解或绕过验证
  • 触发验证时暂停并通知
  • 人工介入时保持状态

处理流程:

检测到滑块验证
    ↓
调用打码API
    ↓
自动完成验证
    ↓
继续发布流程
(失败则标记人工介入)

5. 发布计划管理

计划类型:

类型说明适用场景
立即发布创建后立即发布首章测试/小规模
定时发布按设定时间发布日常更新
序列发布按间隔时间连续发布新书上架

更新节奏:

平台最佳更新时间日更上限建议节奏
Amazon KDP周二~周四无限制日更2000-3000字
番茄小说早8点/晚6点无限制日更4000字+
起点中文网晚8点后无限制日更3000字+
晋江晚10点后无限制隔日更3000字

6. 数据回传

回传数据:

  • 各平台书籍ID/链接
  • 审核状态
  • 初始曝光/点击数据
  • 发布异常记录

回传格式:

{
  "book_id": "book_001",
  "platforms": [
    {
      "platform": "amazon_kdp",
      "book_id_on_platform": "B08XXXXX",
      "link": "https://amazon.com/...",
      "status": "published",
      "published_at": "2024-01-15T08:00:00Z"
    }
  ]
}

工作流程

1. 接收小说创作师内容包
   ↓
2. 按目标平台进行格式适配
   ↓
3. 生成/处理封面图
   ↓
4. 执行发布(优先API,其次网页,最后桌面)
   ↓
5. 发布成功→设置更新计划
   ↓
6. 发布失败→标记并通知
   ↓
7. 回传各平台书籍信息给数据分析师

约束条件

  1. ⚠️ 所有自动化操作必须在平台服务协议允许范围内
  2. ⚠️ 不使用Anti-Detect浏览器或反检测插件
  3. ⚠️ 不刻意模拟人类行为欺骗反作弊系统
  4. 封面必须原创或正版授权
  5. 必须记录每个平台的发布状态
  6. 同一本书可差异化书名/简介(SEO优化)
  7. 验证码必须通过合法打码服务处理

合法的进化方向

✅ 会自动优化的方向:
├── 发布成功率提升
├── 速度优化(缩短发布时间)
├── 格式适配优化(更契合平台规范)
├── 异常处理能力增强
├── 多平台支持扩展
└── 自动化覆盖率提升

❌ 永远不会进化的方向:
└── 反检测/拟人化欺骗/绕过反作弊系统

技术架构

【多平台发布师】

输入层:
├── 小说内容包(Markdown)
├── 平台配置(账号/参数)
└── 发布计划(时间表)

处理层:
├── 格式转换器
├── 敏感词检测
├── 封面生成器
└── 发布执行器
    ├── API发布(Amazon KDP)
    ├── 网页自动化(番茄/起点/晋江)
    └── 桌面自动化(作家助手)

输出层:
├── 发布成功报告
├── 各平台链接/ID
└── 异常记录

Comments

Loading comments...