ClawHub
Back to skill

Security audit

Front

Security checks across malware telemetry and agentic risk

Overview

This Front skill is a disclosed OOMOL connector helper for reading and changing Front contact data, with write operations gated by user confirmation.

Install this only if you trust OOMOL as the connector provider and intend to let Codex access your Front workspace through OOMOL. Review every create or update payload before approving it, and use the one-time CLI install/login/connection steps only when needed.

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
87% confidence
Finding
The trigger text is very broad: it directs the agent to use this skill for any Front-related request, including reading, creating, and updating data. Broad routing increases the chance of unintended invocation in loosely related contexts, which can expose Front data or cause unnecessary state-changing operations if higher-level confirmation logic fails or is inconsistently applied.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.