ClawHub
Back to skill

Security audit

Square

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward Square connector skill that exposes customer and location actions through the OOMOL CLI, with write actions disclosed and gated by user confirmation.

Before installing, users should understand that the skill can read Square customer/location data and, with explicit confirmation, create or update customer records through their connected OOMOL account. Use it only with an OOMOL/Square connection you trust, and review write payloads carefully before approving them.

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
93% confidence
Finding
The trigger text is overly broad and instructs the agent to use this skill for virtually any Square-related task, which can cause unintended invocation in situations where a narrower, safer, or more context-appropriate path should be chosen. In a skill that includes both read and write actions, broad auto-selection increases the chance of unnecessary access to connected account data or accidental progression toward state-changing operations.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.