ClawHub
Back to skill

Security audit

Amazon Seller Zh

Security checks across malware telemetry and agentic risk

Overview

This skill is coherent for Amazon seller operations, but it asks for broad Amazon seller, ads, inventory, and order tooling without clear permission limits or approval rules.

Review before installing. Use this only with narrowly scoped Amazon permissions, keep access read-only unless you intentionally authorize a specific workflow, and require explicit confirmation before changing prices, ads, inventory, listings, or orders.

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 description contains broad search-like activation phrases such as generic Amazon operations questions without clear boundaries on when this skill should be invoked. In agent environments, this can cause over-triggering or unintended routing, leading the skill to activate on loosely related user requests and potentially access seller, inventory, order, or ads tooling in contexts the user did not explicitly intend.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.