ClawHub
Back to skill

Security audit

Monica CRM

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Monica CRM connector with read, write, and delete actions, and it requires confirmation before state-changing actions.

Before installing, confirm you trust OOMOL and the oo CLI with access to your Monica CRM account. Read-only actions may run directly, but creating, updating, or deleting notes should only happen after you review the exact target and payload.

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
95% confidence
Finding
The trigger text is overly broad: it says to use this skill for ANY Monica CRM request and instead of calling the API directly. This can cause the agent to invoke a powerful read/write/destructive skill in situations where a narrower or safer tool selection decision should be made, increasing the chance of unintended data access, modification, or deletion.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.