ClawHub
Back to skill

Security audit

Zorus

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Zorus connector wrapper that uses OOMOL's oo CLI and includes user confirmation guidance for state-changing actions.

Install only if you intend agents to access your Zorus data through OOMOL. Review payloads carefully before approving any write-tagged action, and only complete oo CLI installation, login, or Zorus connection setup when you trust the OOMOL account and connector scopes being used.

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
81% confidence
Finding
The instruction to use this skill for "ANY Zorus request" is overly broad and can cause the agent to route all Zorus-related tasks through a powerful connector without adequate scope checks. In context, this skill supports both reads and state-changing actions, so broad automatic invocation increases the chance of unintended access, overuse of privileged integrations, or accidental execution of write operations.

Static analysis

No suspicious patterns detected.