ClawHub
Back to skill

Security audit

Amazon Keyword Traffic Analysis

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed ZooData Amazon keyword research skill with a broader bundled CLI, but no hidden, destructive, or deceptive behavior was found.

Install this for ZooData-backed Amazon keyword and ASIN traffic research if you are comfortable providing a ZooData API key. Keep usage scoped to the documented keyword workflows unless you intentionally want the bundled CLI's broader product, pricing, market, or review analysis commands.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Tp4

High
Category
MCP Tool Poisoning
Confidence
79% confidence
Finding
The skill claims a narrow keyword-analysis purpose, but the embedded instructions authorize a much broader operational surface including product search, competitor analysis, review access, brand analytics, pricing, listing audit, and market scans. That mismatch can mislead reviewers and users about what the skill may access or infer, increasing the risk of over-collection, unintended data exposure, and execution beyond the user's expected consent boundary.

Description-Behavior Mismatch

Medium
Confidence
90% confidence
Finding
The implementation materially exceeds the declared skill purpose by exposing broad market research, competitor intelligence, review analysis, and composite automation workflows. Scope drift is dangerous because it grants callers more external-data access and operational capability than users or policy reviewers would reasonably expect from a keyword-traffic analysis skill.

Description-Behavior Mismatch

Medium
Confidence
89% confidence
Finding
The review-analysis and prompt-generation toolkit is unrelated to the stated keyword-traffic purpose and introduces a secondary data-processing surface for user-generated review content. That increases privacy, compliance, and misuse risk because the skill can transform and aggregate review text in ways not implied by the manifest.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger guidance includes very broad, natural-language phrases such as general seller questions and generic terms like 'keyword deep dive' or 'is this keyword worth targeting,' which can cause the skill to activate outside a narrowly intended workflow. Over-broad activation is dangerous because it may route unrelated conversations into a tool-enabled analysis path, causing unnecessary data access, misleading outputs, or unintended use of the ZOODATA-backed capability.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.