← 返回 Skills 市场
harrylabsj

ShopGuard

作者 haidong · GitHub ↗ · v1.0.0 · MIT-0
linuxdarwinwin32 ✓ 安全检测通过
113
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install shopguard
功能描述
Cross-platform shopping risk and after-sales decision skill for mainland China that evaluates merchant credibility, hidden post-purchase friction, refund dif...
安全使用建议
This skill is instruction-only and internally consistent: it analyzes links, screenshots, and review snippets to produce a buying verdict and evidence checklist. Before using, avoid sharing account credentials or sensitive personal data in screenshots (addresses, phone numbers); redact or crop those. If you are concerned about autonomous invocation, keep the skill user-invocable only or use platform controls to restrict when it runs.
功能分析
Type: OpenClaw Skill Name: shopguard Version: 1.0.0 The ShopGuard skill bundle is a well-documented set of instructions and reference materials designed to help an AI agent evaluate merchant credibility and after-sales risks on Chinese e-commerce platforms. The logic focuses entirely on analyzing public listing data, seller badges, and user-provided screenshots to provide shopping advice. Crucially, the SKILL.md file includes an explicit 'Safety Boundary' section that forbids the agent from logging into user accounts, chatting with sellers, or placing orders, and there is no evidence of data exfiltration or malicious execution patterns.
能力评估
Purpose & Capability
The name/description ask for seller-risk, refund-friction, and evidence advice; the skill is instruction-only and asks the agent to analyze links, screenshots, seller badges, and review snippets — all coherent with its stated purpose. No unrelated credentials, binaries, or platform-level access are requested.
Instruction Scope
SKILL.md instructs the agent to evaluate product links, screenshots, review excerpts, price gaps and return a decisive verdict plus an evidence checklist. It does not direct reading of system files, environment variables, or transmission to outside endpoints beyond normal user-provided inputs.
Install Mechanism
No install spec and no code files — lowest-risk deployment model. Nothing is downloaded or written to disk by the skill itself.
Credentials
The skill declares no required environment variables, credentials, or config paths, which is appropriate for its described function of analyzing user-provided shopping artifacts.
Persistence & Privilege
always is false and the skill does not request elevated persistence or cross-skill configuration. Autonomous invocation is allowed by default (platform behavior) but is not combined with other red flags here.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install shopguard
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /shopguard 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
Initial English release of ShopGuard, a shopping risk and after-sales decision skill that checks seller trust, refund friction, gifting and urgency fit, and what evidence to save before ordering.
元数据
Slug shopguard
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

ShopGuard 是什么?

Cross-platform shopping risk and after-sales decision skill for mainland China that evaluates merchant credibility, hidden post-purchase friction, refund dif... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 113 次。

如何安装 ShopGuard?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install shopguard」即可一键安装,无需额外配置。

ShopGuard 是免费的吗?

是的,ShopGuard 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

ShopGuard 支持哪些平台?

ShopGuard 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(linux, darwin, win32)。

谁开发了 ShopGuard?

由 haidong(@harrylabsj)开发并维护,当前版本 v1.0.0。

💬 留言讨论