Ai Intelligent Fraud Detection — 实用工具
v1.0.0Ai Intelligent Fraud Detection是一款实用的工具技能，能够帮助用户完成相关任务，提升工作效率。
0· 124·0 当前·0 累计
by 安全扫描
OpenClaw
可疑
medium confidenceThe skill describes a fraud-detection service but provides no code and instructs users to clone and run an external GitHub repository — this mismatch and the instruction to execute remote code are concerning.
评估建议
This skill is an instruction-only wrapper that tells you to git clone and run a GitHub project that is not bundled with the skill. Before installing or running it: (1) verify the GitHub repository identity and review its code (especially app.py and requirements.txt) for malicious behavior; (2) prefer a packaged skill that includes its code or references a pinned release tag; (3) run the cloned project in a sandbox or isolated environment and inspect network calls and required credentials; (4) do...详细分析 ▾
ℹ 用途与能力
Name/description claim a complete AI fraud-detection system; however the packaged skill contains no runnable code and instead tells the user/agent to git clone a separate GitHub repo. Calling out/launching external software could be legitimate but is not proportional to an instruction-only skill that otherwise provides no implementation or provenance.
⚠ 指令范围
SKILL.md instructs cloning https://github.com/openclaw-skills/ai-intelligent-fraud-detection, pip installing dependencies, and running python app.py. Those steps cause the agent/operator to download and execute arbitrary remote code not included in the skill, which expands runtime scope beyond the declared package and could execute any system actions or exfiltrate data.
⚠ 安装机制
No install spec in the registry, but the runtime instructions require fetching code from GitHub and running pip install -r requirements.txt. While GitHub is a common host, fetching and executing code at runtime without bundled sources or pinned releases increases risk (unknown repo owner, unknown commit/branch, unknown dependencies).
ℹ 凭证需求
The skill declares no required environment variables or credentials, which is consistent on its face. However, the external code it directs you to run may request secrets or network access at runtime; that possibility is not documented in the SKILL.md and therefore not proportionate to the minimal declared requirements.
✓ 持久化与权限
The skill does not request always:true, nor does it declare modifications to agent/system configs. It relies on the operator to run an external service, so it does not itself request elevated or persistent platform privileges.
安全有层次，运行前请审查代码。
运行时依赖
无特殊依赖
安装命令
点击复制官方npx clawhub@latest install ai-fraud-detect
镜像加速npx clawhub@latest install ai-fraud-detect --registry https://cn.longxiaskill.com 镜像可用
本土化适配说明
Ai Intelligent Fraud Detection — 实用工具 安装说明： 安装命令：["openclaw skills install ai-fraud-detect","npx clawhub@latest install ai-fraud-detect"]