Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
publish test
v1.0.0Search products across 8 Chinese e-commerce platforms: Taobao, Tmall, JD, PDD, 1688, AliExpress, Douyin, XHS. Zero-config — no API keys needed. Powered by Sh...
⭐ 0· 36·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
The skill claims zero-config product search across Chinese platforms via a Shopme database — that matches the described tools (search_products, get_product_detail) and the optional SHOPME_API_BASE. However the SKILL.md expects an MCP server installed via 'npx @shopmeagent/cn-ecommerce-search-mcp', implying the npx runtime is required even though the registry metadata lists no required binaries. This is an inconsistency (npx should be declared).
Instruction Scope
The SKILL.md instructs adding an mcpServers entry that runs 'npx -y @shopmeagent/cn-ecommerce-search-mcp'. That means at runtime arbitrary code will be fetched from the npm registry and executed. Aside from that, the rest of the instructions stay on purpose and do not ask to read unrelated files or credentials. The one-step to fetch/run an external package is the problematic scope expansion.
Install Mechanism
There is no install spec in the registry, but the skill instructs use of npx to fetch and run '@shopmeagent/cn-ecommerce-search-mcp'. Using npx executes remote package code on demand — a moderate-to-high risk install mechanism because the package will be pulled from the public npm registry and executed without a pinned, reviewed release in this manifest. The registry metadata does not declare this install requirement.
Credentials
The skill declares no required credentials and only an optional SHOPME_API_BASE override. That is proportionate to a read-only product-search service. No extra secrets or unrelated environment variables are requested.
Persistence & Privilege
always is false (normal). The SKILL.md asks you to add an mcpServers entry to the agent config (a persistent configuration change), which would cause the agent to run an external package when the skill is used. This persistent hook combined with remote package execution increases risk compared to a pure instruction-only skill, but 'always' is not set so it is not force-included.
What to consider before installing
This skill appears to do what it says (search Chinese e-commerce) but it asks you to fetch/run an external npm package via npx at runtime — something not declared in the registry metadata. npx will pull and execute code from the npm registry, which can perform any action your account/host permits. Before installing or enabling: 1) Ensure you have npx available or update the skill manifest to declare it. 2) Inspect the source of @shopmeagent/cn-ecommerce-search-mcp (npm package repo) and prefer a pinned release. 3) If possible, run the MCP package in an isolated/dev environment first (or set SHOPME_API_BASE to a vetted endpoint). 4) Be cautious about allowing the agent to autonomously invoke the skill since that will execute external code on demand. If you cannot review the npm package source or trust its publisher, treat this as higher risk and avoid installing.Like a lobster shell, security has layers — review code before you run it.
latestvk97dbjhr9m5d1tvsh14fejvax984wkp5
License
MIT-0
Free to use, modify, and redistribute. No attribution required.