Fake Foreign Health Audit — Security skill for Claude Code
OpenClaw skill:鉴别药品/保健品是否为「假洋货」(伪造洋品牌身份).
How to install Fake Foreign Health Audit
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open longppai68-ai/fake-foreign-health-audit and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Fake Foreign Health Audit does
OpenClaw skill:鉴别药品/保健品是否为「假洋货」(伪造洋品牌身份)。覆盖 9 个法域的官方数据库、工商登记与渠道核查。
Alternatives in Security
- Pal — Multi-model AI integration — chat, debugging, code review, planning, security audit 11.3k ★
- Skills Audit Report — Date: 2026-02-15 Auditor: Automated Skill Quality Audit Scope: Recently added skills in business-growth/, fina 5.3k ★
- Om Vault Audit — Vault Audit 4.6k ★
README
fake-foreign-health-audit
鉴别「药品 / 保健品」是不是**假洋货**(伪造洋品牌身份)的 OpenClaw 技能。
[](https://openclaw.ai) [](#安装) [](https://github.com/longppai68-ai/fake-foreign-health-audit) [](https://github.com/longppai68-ai/fake-foreign-health-audit/releases/latest) [](https://github.com/longppai68-ai/fake-foreign-health-audit/releases) [](https://www.python.org/) [-brightgreen)](#依赖) [](LICENSE)
给它一个商品链接、包装照片或品牌名,它去查**宣称国的官方数据库、工商登记和本土渠道**,出一份带证据分级的鉴定报告。
**不做医疗建议,只做身份与合规核查。**
目录
为什么需要它
"XX国进口""XX国品牌"是保健品电商最常见的溢价理由,也是最容易造假的标签。但**判断它真假并不需要专业背景**——只是需要知道去**哪里查**,以及**怎么读查到的结果**。
难点在两个地方:
- 各国的监管结构完全不同,打法必须换。 加拿大有上市前强制许可(NPN),查一下就知道持证人是谁、剂量多少;德国没有产品级审批,查注册号这条路根本不存在,得改查工商登记的「经营范围」。
- "查不到"和"不存在"是两回事。 大量站点有反爬(403 / 人机验证 / JS 壳页)。把"没查到"当成"没有",会冤枉真实品牌;反过来,把"有个注册号"当成"是真洋品牌",会放过假洋货——注册号是可以合法申请的。
这个 skill 把这两件事都固化成了流程:按国家切换核查路径,并且强制标注证据强度。
核心框架
三层分开验
| 层次 | 要回答的问题 | 若为否 |
|---|---|---|
| 身份层 | 品牌的控制主体,在不在它宣称的国家? | 洋品牌身份是包装出来的 |
| 实质层 | 是否取得该国合法资质、按当地标准生产? | 可能连合法身份都没有 |
| 存在层 | 在该国本土是否真有渠道、消费者、口碑? |
Related Skills
Openclaw Ops
OpenClaw operations skill with health checks, repair scripts, watchdogs, update triage, and security scans.
Close Gold Gap
Emit the deterministic remediation recipe for one gold-audit gap — scaffold/test/config/process, never a fake
Levelup
Raise the project's gold level honestly — gold-audit → remediation wave → close each gap for real → re-audit b
Token Scan
Meme coin and token security scan — checks for rug pull vectors (hidden mint, honeypot, fee manipulation, LP l
PsyLinks 360 Security
Stop shipping insecure AI-generated code. This free skill teaches Claude & AI IDEs secure coding by default an
Amazon Skills
Free AI agent skills for Amazon sellers— keyword research, competitor analysis, listing audit & more. Works wi
Related Agents
Openclaw Debugger
Use when an OpenClaw instance has a problem the health sentinel couldn't fix — gateway failures, config drift,
Rayo Heartbeat Watcher
Check OpenClaw gateway health and alert if Rayo is dead or idle too long. Monitors ~/.openclaw/logs/gateway.lo
Light Review FakeTest
Audit a Delphi DUnitX or classic-DUnit test suite for FAKE or WEAK tests — tests that pass without verifying t