Skill flagged — suspicious patterns detected

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

技能使用积分榜

v1.2.0

技能使用积分榜 v1.2 — OpenClaw 技能使用追踪与积分管理系统。 触发场景: (1) 用户询问技能使用榜单、积分统计 (2) 用户要求查看技能调用记录、错误日志 (3) 用户要求查看某技能的使用详情 (4) 用户要求生成每日/历史积分报告 (5) 用户询问"今天情况如何"、"工作流复盘" 核心功能:...

0· 52·0 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 luis1213899/skill-scoreboard.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "技能使用积分榜" (luis1213899/skill-scoreboard) from ClawHub.
Skill page: https://clawhub.ai/luis1213899/skill-scoreboard
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 skill-scoreboard

ClawHub CLI

Package manager switcher

npx clawhub@latest install skill-scoreboard
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Suspicious
medium confidence
Purpose & Capability
Name/description match the implementation: the script enumerates SharedSkills, computes a complexity weight, records calls and errors, and produces leaderboards/snapshots. No unrelated credentials or binaries are requested.
Instruction Scope
SKILL.md instructs running the included Python script for recording, querying, daily snapshot and review. The runtime instructions and CLI examples align with the provided script. The instructions require access to ~/SharedSkills and write to ~/.skill_scoreboard; that is consistent with the stated purpose but does mean the skill will read metadata of all skills in the user's SharedSkills directory and create files under the user's home.
Install Mechanism
No install spec; this is essentially an instruction + script bundle. No network downloads or package installs are requested by the manifest. Risk from install mechanism is low.
Credentials
The skill requires no environment variables or external credentials. It reads the SharedSkills directory and skill files (md, js, py, sh, json) to compute complexity—this is proportionate to the described functionality.
!
Persistence & Privilege
The skill writes persistent state and logs under ~/.skill_scoreboard (scores.json, logs, daily snapshots). That is expected for a tracker, but users should be aware files will be created and updated daily. The skill is not marked always:true and does not request elevated system privileges, which is appropriate.
What to consider before installing
The skill appears to be a legitimate local tracker: it reads your ~/SharedSkills to compute weights and writes logs and JSON snapshots to ~/.skill_scoreboard. Before installing, review the complete script (the provided file was truncated in the manifest) to ensure the missing tail doesn't contain network calls or data exfiltration. Confirm you are comfortable granting read access to your SharedSkills folder and creating persistent files in your home directory. If you proceed, consider running the script in a restricted environment (or inspect the full file contents) and back up or inspect any existing ~/.skill_scoreboard data first.

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

automationvk97f836pnkaam85nmrb1bs333185q66clatestvk97f836pnkaam85nmrb1bs333185q66cscoreboardvk97f836pnkaam85nmrb1bs333185q66cstatsvk97f836pnkaam85nmrb1bs333185q66ctrackingvk97f836pnkaam85nmrb1bs333185q66c
52downloads
0stars
2versions
Updated 12h ago
v1.2.0
MIT-0

技能使用积分榜

概述

本技能用于追踪和记录 OpenClaw 中所有技能的使用情况,并根据调用时长和复杂度计算积分。

积分规则

积分 = 1 × (调用时间秒 / 技能复杂度权重)

复杂度权重由技能文件的规模决定(归一化到 [0.95, 0.9975]):

  • 最小权重:0.9500
  • 最大权重:0.9975
  • 任意两技能权重差距 ≤5%
  • 计算方式:原始分数 → 对数缩放 → min-max 归一化

权重越高,相同时间获得的积分越少(复杂技能调用成本更高)

文件结构

skill-scoreboard/
├── SKILL.md                      # 本文档
└── scripts/
    └── score_tracker.py          # 核心追踪脚本

使用方式

1. 手动记录技能调用

python3 ~/SharedSkills/skill-scoreboard/scripts/score_tracker.py record \
  --skill <技能名> \
  --duration <调用时长(秒)> \
  --success <true|false> \
  --error <错误信息(可选)>

2. 查询全局榜单

python3 ~/SharedSkills/skill-scoreboard/scripts/score_tracker.py leaderboard --limit 10

3. 查询今日榜单

python3 ~/SharedSkills/skill-scoreboard/scripts/score_tracker.py today

4. 生成每日快照

python3 ~/SharedSkills/skill-scoreboard/scripts/score_tracker.py daily

5. 查看技能详情

python3 ~/SharedSkills/skill-scoreboard/scripts/score_tracker.py detail --skill <技能名>

6. 查看所有技能权重

python3 ~/SharedSkills/skill-scoreboard/scripts/score_tracker.py weight

7. 每日工作流复盘报告

python3 ~/SharedSkills/skill-scoreboard/scripts/score_tracker.py review

定时任务

用户可通过 OpenClaw cron 功能设置每日定时执行:

# 每日23:00自动执行
openclaw cron add \
  --name "每日技能积分榜复盘" \
  --schedule "0 23 * * *" \
  --tz "Asia/Shanghai" \
  -- python3 ~/SharedSkills/skill-scoreboard/scripts/score_tracker.py daily && \
     python3 ~/SharedSkills/skill-scoreboard/scripts/score_tracker.py review

数据存储

文件/目录内容
~/.skill_scoreboard/scores.json所有技能的积分数据
~/.skill_scoreboard/logs/calls.log调用日志
~/.skill_scoreboard/logs/errors.log错误日志
~/.skill_scoreboard/daily/每日快照目录

使用示例

场景1:用户问"今天用了哪些技能"

python3 ~/SharedSkills/skill-scoreboard/scripts/score_tracker.py today

场景2:用户问"哪个技能最常用"

python3 ~/SharedSkills/skill-scoreboard/scripts/score_tracker.py leaderboard --limit 5

场景3:用户问"xia-zhua-zhua 用得怎么样"

python3 ~/SharedSkills/skill-scoreboard/scripts/score_tracker.py detail --skill xia-zhua-zhua

场景4:用户想看完整的历史统计

python3 ~/SharedSkills/skill-scoreboard/scripts/score_tracker.py leaderboard --limit 20

Comments

Loading comments...