ClawHub
Back to skill

Security audit

LiveAgent

Security checks across malware telemetry and agentic risk

Overview

This LiveAgent skill is a coherent connector wrapper with disclosed read and write actions and clear confirmation requirements for state-changing operations.

Before installing, understand that this skill can create and update LiveAgent contacts and tickets through your connected OOMOL account. Let read-only actions run normally, but review and confirm exact payloads before any create or update action, and only run the oo CLI install or login steps if setup actually fails.

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
92% confidence
Finding
The description says to use this skill for ANY LiveAgent request and instead of calling the API directly, which is an overly broad trigger phrase that can cause the agent to invoke the skill in situations where a narrower or safer path would be more appropriate. Because this skill supports both read and write operations, broad auto-selection increases the chance of unintended state-changing actions or bypassing more context-specific safeguards.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.