ClawHub
Back to skill

Security audit

Printify

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward Printify connector guide that reads merchant data through OOMOL, with minor documentation issues but no hidden or destructive behavior found.

Before installing, understand that this skill can access Printify shop, product, and order information through your connected OOMOL account. Confirm any action that is tagged as write, and treat order retrieval as potentially sensitive because order records may include customer or business data.

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 (2)

Intent-Code Divergence

Medium
Confidence
92% confidence
Finding
The skill labels `get_order` as `[write]` even though it is described as a retrieval operation. Misclassifying a read action as state-changing can cause the agent or operator to apply the wrong approval policy, reduce trust in the documentation, and create confusion around which operations are actually safe versus risky. In a connector skill that mediates access to a live commerce account, inaccurate safety labeling weakens operational safeguards.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The description instructs agents to use this skill for ANY Printify request and instead of calling the API directly, which is an overly broad trigger. This can cause unintended invocation on casual mentions of Printify or route tasks through the skill without sufficient task-specific validation, increasing the chance of unnecessary account access or accidental execution of connector actions. Because the skill can read and potentially modify merchant data, broad activation makes misuse more likely.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.