xianyu-api-client-skill

Security checks across malware telemetry and agentic risk

Overview

This is a transparent Xianyu API client whose account-changing powers and unsafe automation methods are disclosed and scoped to the stated marketplace API.

Install this only for Xianyu shop automation. Use dedicated least-privilege Xianyu credentials, prefer the confirmed methods and dry-run mode, and only allow _unsafe methods in controlled automation where you have already approved the exact product or order changes.

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
92% confidence
Finding
The `request_unsafe` path explicitly bypasses the confirmation control for high-risk write operations and can send arbitrary allowed payloads directly to the remote API. In an agent/automation context, this weakens the claimed safety model because callers may invoke destructive actions like delete, modify price, or logistics submission without any user-facing approval at the call site.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal