ClawHub
Back to skill

Security audit

SupportBee

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed SupportBee connector skill that can read and change support-desk data through OOMOL, with explicit confirmation guidance for write and destructive actions.

Install this only if you want agents to operate your SupportBee account through OOMOL. Read-only actions are described as safe to run directly, but creating replies, comments, tickets, users, updates, or removing labels can affect customer-support records, so confirm the exact payload before allowing those actions.

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
83% confidence
Finding
The instruction to use this skill for ANY SupportBee request is overly broad and can suppress safer, more context-aware handling by forcing all SupportBee-related tasks through a single high-privilege integration. In a skill that supports reading, creating, updating, and deleting data, this broad routing increases the chance of unintended state-changing or destructive operations being selected without sufficient scrutiny.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.