ClawHub
Back to skill

Security audit

Make

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Make.com connector that can read account and scenario information and perform scenario operations through OOMOL's CLI.

Install only if you are comfortable letting agents use your OOMOL-connected Make account. Review scenario activation, deactivation, and one-time run requests carefully, because Make scenarios can trigger downstream actions in other services.

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 skill description instructs the agent to use this skill for ANY Make-related request, creating an overly broad routing rule that can bypass more specific safeguards or narrower-purpose skills. Because this connector includes both read and state-changing actions, broad auto-selection increases the chance of unintended activation, deactivation, or scenario execution in contexts where the user did not explicitly intend operational changes.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal