ClawHub
Back to skill

Security audit

FlowiseAI

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed FlowiseAI connector skill that uses OOMOL's oo CLI and has no artifact evidence of hidden or malicious behavior.

Install this only if you trust OOMOL and want your agent to use your connected FlowiseAI account. Review any send_message payload before approval, and verify the oo CLI installer source if you need first-time setup.

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
90% confidence
Finding
The skill description says to use this skill for ANY FlowiseAI request and instead of calling the API directly, which creates a very broad routing trigger. This can cause the agent to invoke the skill in situations where FlowiseAI is only loosely referenced, increasing the chance of unintended execution of connector-backed actions and bypassing more context-appropriate handling.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.