ClawHub
Back to skill

Security audit

Dataify Amazon Global Product

Security checks across malware telemetry and agentic risk

Overview

This skill clearly submits Amazon product collection jobs to Dataify using a Dataify token, and I found no hidden destructive or unrelated behavior.

Before installing, treat DATAIFY_API_TOKEN as a secret, avoid persistent storage on shared machines unless you accept that risk, and review task parameters carefully because the skill can create Dataify collection jobs in your account.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
85% confidence
Finding
The skill explicitly instructs the agent to access environment variables and make outbound network requests, yet no declared permissions are present. This creates a governance and sandboxing gap: users or hosting platforms may not realize the skill can read local secrets and transmit data externally, increasing the risk of unintended secret exposure or unauthorized external actions.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill tells users to save a long-lived API token in DATAIFY_API_TOKEN, including a persistent user-level Windows environment variable, but does not warn about credential sensitivity, local persistence, or exposure to other local processes. If the host is shared, compromised, or logs environment values, the token could be stolen and reused to create tasks or access the user's Dataify account resources.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger description is overly broad and includes generic scraping and collection phrases, which can cause the skill to activate for loosely related user requests rather than only explicit Dataify Amazon-product tasks. Mis-triggering can route users into an external task-submission workflow unexpectedly, increasing the chance of unintended data collection actions, token-handling prompts, or confusion about which tool is being invoked.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.