JD.com Product Details API

Security checks across malware telemetry and agentic risk

Overview

This is a narrow JD.com product lookup skill, with the main caveat that its API token is sent in the URL because the vendor endpoint requires it.

Use a scoped, revocable JustOneAPI token and avoid running this skill where full URLs may be captured in shared logs, shell history, monitoring, or screenshots. Treat request URLs as sensitive because the vendor API uses token-in-query authentication.

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 (1)

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill sends the API token in the URL query string, which is routinely exposed through logs, browser/history artifacts, reverse proxies, observability tooling, and upstream services. Although the request uses HTTPS, query parameters are still more broadly recorded than headers, so the token can be unintentionally disclosed and reused.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal