ClawHub
Back to skill

Security audit

Taobao and Tmall Product Search API

Security checks across malware telemetry and agentic risk

Overview

This is a narrow JustOneAPI Taobao/Tmall product-search skill with a real but disclosed token-handling risk.

Install only if you trust JustOneAPI and are comfortable sending searches and a JustOneAPI token to api.justoneapi.com. Use a dedicated, rotatable token and avoid exposing full command lines or request URLs in chat, screenshots, shell history, debug logs, or shared terminals.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill defines the API access token as a query parameter and later appends all query parameters directly into the request URL. Secrets in URLs are commonly exposed through logs, monitoring systems, browser/history artifacts, proxy caches, and upstream infrastructure, so the token can be leaked even when HTTPS is used.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The operation sends a required access token to an external service via a query parameter, which is commonly logged by clients, proxies, servers, and observability tooling. Because the manifest gives no user-facing warning or safer handling guidance, it increases the chance of inadvertent credential disclosure to third parties or through logs.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
Documenting an access token as a query parameter is risky because query strings are commonly logged by clients, proxies, gateways, browser history, and monitoring systems, increasing the chance of credential leakage. In an agent skill context, this is more dangerous because model/tool traces or debugging output may inadvertently capture full request URLs containing the token.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.