ClawHub
Back to skill

Security audit

lingxiao-amazon-ads-check

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Amazon ads report-analysis helper that sends user-provided search term reports to a stated external MCP service, with no hidden install scripts or credential access in the artifact.

Before installing, understand that using the MCP tools means sending your Amazon ads search term report text to lingxiaochuhai.com. Avoid uploading reports containing data you are not allowed to share, and keep decisions such as negative keywords under human review as the skill itself recommends.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The skill description contains broad activation triggers such as users asking about launching Amazon ads, ad optimization, negation keywords, where ad spend went, whether common advice is correct, or analyzing search term reports. These overlap with many routine advertising-assistance requests, increasing the chance the skill is invoked when not specifically intended, which can cause unnecessary external MCP usage and irrelevant guidance.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.