ClawHub
Back to skill

Security audit

Cin7 Core

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed read-only connector for Cin7 Core data through OOMOL, with no artifact evidence of hidden persistence, exfiltration, or destructive behavior.

Install this only if you want your agent to read Cin7 Core account, customer, and product data via your OOMOL connection. Be aware that the routing language is broad, so you may want to give your agent explicit instructions to use it only when you ask to retrieve or inspect Cin7 Core data.

SkillSpector

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
88% confidence
Finding
The instruction to use this skill for "ANY Cin7 Core request" is an overly broad routing trigger that can cause the agent to invoke the skill whenever Cin7 Core is merely mentioned, even when the user did not intend tool use or when direct reasoning would be more appropriate. In this skill, the risk is moderated because the listed actions are read-only, but unintended invocation can still expose connected account data or create privacy and authorization issues through unnecessary access.

Static analysis

No suspicious patterns detected.