Skill flagged — suspicious patterns detected

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

Openclaw Itsm Skill

v0.1.0

分析嘉为蓝鲸 ITSM 工单数据,提供新工单处理建议、趋势报表、高频问题识别及 SLA 超时风险监控,支持多流程字段自动映射。

0· 307·0 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 michaeljochen/openclaw-itsm-skill.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Openclaw Itsm Skill" (michaeljochen/openclaw-itsm-skill) from ClawHub.
Skill page: https://clawhub.ai/michaeljochen/openclaw-itsm-skill
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

Canonical install target

openclaw skills install michaeljochen/openclaw-itsm-skill

ClawHub CLI

Package manager switcher

npx clawhub@latest install openclaw-itsm-skill
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Suspicious
medium confidence
Purpose & Capability
The skill's stated goal—analyzing BlueKing ITSM tickets, trend reports, clustering, and SLA monitoring—matches the instructions. Optional environment variables (BK_ITSM_API_*, WEBHOOK_URL) are relevant to the described integrations. However, the skill references many helper scripts, reference files, and a config.json that are not present in the package or metadata, which is inconsistent with a self-contained skill.
!
Instruction Scope
SKILL.md instructs the agent to run commands like `python scripts/analyze_ticket.py` and to read CSV/Excel exports and reference files. Because this is an instruction-only skill with no accompanying scripts or references, it's unclear what will actually run. The instructions also include optional pushing of reports to an external webhook (enterprise WeChat), which would transmit potentially sensitive ticket data off-site if configured. The instructions do not tell the agent to access unrelated system files, but their reliance on non-provided artifacts grants broad discretion and is unsafe without review.
Install Mechanism
There is no install spec (instruction-only), so nothing is written to disk by the installer. This is low-risk in isolation, but combined with missing scripts it raises a usability/security concern: the skill expects local scripts to exist yet does not install or provide them.
!
Credentials
The metadata lists no required environment variables, but SKILL.md documents optional env vars BK_ITSM_API_URL, BK_ITSM_API_KEY and WEBHOOK_URL. Requesting an ITSM API key and optional webhook is reasonable for integrations, but the mismatch between declared requirements (none) and the instructions (which reference sensitive credentials) is inconsistent. The webhook option especially enables data exfiltration if set to an external URL; users should only provide such secrets after verifying the scripts that will use them.
Persistence & Privilege
The skill does not request always: true and does not indicate writing to other skills' configs or system-wide settings. It appears to be invokable by the user and may be invoked autonomously (platform default), which increases risk if scripts are supplied by an unknown source, but the skill itself does not request elevated persistence.
What to consider before installing
This skill's description and instructions align with an ITSM analysis tool, but the package is instruction-only and does not include the referenced Python scripts, config files, or reference documentation. Before installing or running it: 1) Ask the publisher for the missing scripts and a dependency list (Python version, required pip packages) and review their code for data-handling and network calls. 2) Do not provide BK_ITSM_API_KEY or WEBHOOK_URL until you have inspected the scripts; a webhook may send sensitive ticket data externally. 3) If you plan to run the scripts, run them in an isolated environment (sandbox/container) and audit outbound network traffic. 4) Prefer a version that bundles the implementation or points to a trusted repository (e.g., GitHub) with release artifacts you can inspect. If the publisher cannot provide the missing artifacts or a trustworthy source, treat this skill as incomplete and avoid using it with real ticket data.

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

latestvk97ckzk03pgsh51zpdmpa3837982pzpv
307downloads
0stars
1versions
Updated 17h ago
v0.1.0
MIT-0

嘉为蓝鲸 ITSM 工单分析技能

何时使用

使用此技能当:

  • 需要分析嘉为蓝鲸 ITSM 工单数据
  • 为新收到的工单提供处理建议
  • 生成工单日报/周报/月报
  • 识别高频问题/重复问题
  • 监控 SLA 超时风险
  • 工单分类/自动路由建议
  • 不同流程的工单分析(字段自动适配)

不使用此技能当:

  • 需要直接操作 ITSM 系统(创建/关闭工单)→ 需要 API 集成
  • 实时工单通知 → 需要 Webhook 集成

数据输入方式

方式 1:CSV/Excel 导出(推荐)

从嘉为蓝鲸 ITSM 导出工单数据:

# 在蓝鲸 ITSM 后台:工单管理 → 导出 → 选择字段

⚠️ 重要:不同流程的工单字段可能不同

技能会自动识别和映射字段,你只需要导出包含以下基础字段即可:

嘉为蓝鲸标准字段说明必填
单号工单唯一标识
标题工单标题/摘要
服务目录一级分类(如:IT 服务)
服务二级分类(如:网络服务)
服务类型三级分类(如:VPN 问题)
状态工单状态(待处理/处理中/已解决)
当前步骤流程节点名称
当前处理人当前负责人
创建人提单人
提单时间创建时间
结束时间解决/关闭时间
挂起时间暂停时间
恢复时间恢复处理时间
流程版本流程模板版本

可选字段(如有则提供更详细分析):

  • 优先级(P0/P1/P2/P3)
  • SLA 截止时间
  • 工单描述/详细内容
  • 解决方案/处理记录

方式 2:不同流程的工单混合分析

技能支持混合分析不同流程的工单:

  • 事件管理流程
  • 请求管理流程
  • 变更管理流程
  • 问题管理流程
# 导出时可以选择多个流程的工单
# 技能会自动识别"服务目录/服务/服务类型"进行分类

核心功能

1. 字段智能映射

自动识别嘉为蓝鲸标准字段,支持不同流程的工单:

# 自动映射示例
字段映射 = {
    "单号": "ticket_id",
    "标题": "title",
    "服务目录": "service_catalog",      # 一级分类
    "服务": "service",                  # 二级分类
    "服务类型": "service_type",         # 三级分类
    "状态": "status",
    "当前步骤": "current_step",
    "当前处理人": "assignee",
    "创建人": "requester",
    "提单时间": "created_at",
    "结束时间": "resolved_at",
    "挂起时间": "suspended_at",
    "恢复时间": "resumed_at",
    "流程版本": "process_version"
}

2. 新工单处理建议

当有新工单时,自动分析并给出建议:

# 读取新工单数据
python scripts/analyze_ticket.py --input /path/to/new_ticket.csv

# 输出示例:
# - 工单类型:网络问题
# - 建议分类:基础设施组
# - 相似历史工单:3 个
# - 推荐解决方案:检查交换机配置...
# - 预计处理时长:2 小时

3. 深度分析(完整报告)

处理人工作量统计

  • 处理人分布(工单数/占比)
  • 每个处理人的工单列表
  • 工作量对比

响应时间分析

  • 已解决工单:平均响应时间、最快/最慢
  • 未解决工单:平均等待时间、最长等待
  • Top 5 最慢工单列表

问题分类统计

  • 自动关键词分类(登录问题、服务宕机、监控告警等)
  • 分类占比统计
  • 重复问题识别
# 生成深度分析报告
python scripts/deep_analysis.py --input /path/to/tickets.xlsx

4. 工单趋势分析(支持多流程)

生成日报/周报/月报,按服务目录/服务/服务类型分层分析

# 生成日报
python scripts/trend_analysis.py --input /path/to/tickets.csv --period daily

# 生成周报(按服务分类)
python scripts/trend_analysis.py --input /path/to/tickets.csv --period weekly --group-by service

分析指标:

  • 工单总量趋势
  • 平均响应时间(提单时间 → 首次处理)
  • 平均解决时间(提单时间 → 结束时间)
  • 一次解决率
  • SLA 达标率
  • 按服务目录/服务/服务类型分布
  • 按流程节点分布
  • 处理人工作量
  • 挂起率分析

5. 高频问题识别(按服务类型聚类)

识别重复问题,帮助建立知识库:

python scripts/cluster_issues.py --input /path/to/tickets.csv --threshold 0.8

输出:

  • 高频问题 Top 10(按服务类型分组)
  • 问题聚类分组
  • 推荐知识库文章
  • 重复提单识别

6. SLA 监控(考虑挂起时间)

监控即将超时/已超时的工单,自动扣除挂起时间

python scripts/sla_monitor.py --input /path/to/tickets.csv --warning-hours 4

输出:

  • 即将超时工单列表(<4 小时)
  • 已超时工单列表
  • 超时原因分析(处理慢/挂起久/其他)
  • 实际处理时长 vs SLA 承诺

脚本说明

脚本功能输入输出
analyze_ticket.py单工单分析CSV/JSON处理建议
trend_analysis.py趋势分析CSVMarkdown 报告
cluster_issues.py问题聚类CSV聚类结果
sla_monitor.pySLA 监控CSV预警列表

配置说明

环境变量(可选)

# 嘉为蓝鲸 ITSM API 配置
export BK_ITSM_API_URL="https://<your-domain>/api/v1/itsm"
export BK_ITSM_API_KEY="your-api-key"

# 企业微信推送(可选)
export WEBHOOK_URL="https://qyapi.weixin.qq.com/cgi-bin/webhook/send?key=xxx"

配置文件

编辑 references/config.json 自定义:

{
  "ticket_types": {
    "网络问题": "基础设施组",
    "服务器问题": "系统运维组",
    "应用故障": "应用支持组",
    "权限申请": "安全组"
  },
  "sla_hours": {
    "P0": 1,
    "P1": 4,
    "P2": 24,
    "P3": 72
  }
}

使用示例

示例 1:分析新工单

用户:分析这个新工单,给出处理建议
[上传工单 CSV]

→ 自动调用 analyze_ticket.py
→ 输出:工单类型、建议分类、相似工单、解决方案

示例 2:生成工单日报

用户:生成昨天的工单日报

→ 自动调用 trend_analysis.py --period daily
→ 输出:Markdown 格式日报,可推送到企业微信

示例 3:识别高频问题

用户:最近有哪些高频问题?

→ 自动调用 cluster_issues.py
→ 输出:Top 10 高频问题 + 聚类分组

示例 4:SLA 预警

用户:有哪些工单快超时了?

→ 自动调用 sla_monitor.py
→ 输出:即将超时工单列表 + 处理建议

输出模板

工单日报模板

## 📊 ITSM 工单日报

**日期**: 2026-03-11

### 核心指标
- 新增工单:**15 个** (↑2 个)
- 已解决:**12 个** (80%)
- 平均响应时间:**25 分钟** (↓5 分钟)
- SLA 达标率:**93%**

### 工单类型分布
1. 网络问题:5 个
2. 服务器问题:4 个
3. 应用故障:3 个
4. 权限申请:3 个

### 高频问题 Top 3
1. VPN 连接失败 (3 次)
2. 邮箱无法登录 (2 次)
3. 打印机无法连接 (2 次)

### 即将超时预警
- 工单 #12345:剩余 2 小时 (P1)
- 工单 #12346:剩余 3 小时 (P2)

参考资料

  • 嘉为蓝鲸文档: references/blueking-api.md
  • 工单分类规则: references/ticket-classification.md
  • SLA 策略: references/sla-policy.md

企业微信推送

和新闻推送一样,可以配置定时推送:

# 每天早上 9 点推送昨天的工单日报
cron: 0 9 * * *

推送配置参考 references/webhook-config.md

Comments

Loading comments...