ClawHub
Back to skill

Security audit

Voiceflow

Security checks across malware telemetry and agentic risk

Overview

This Voiceflow skill is a coherent connector skill that uses OOMOL's oo CLI for user-directed Voiceflow actions, with disclosed credentials handling and write-confirmation guidance.

Install only if you intend to let Codex use your OOMOL-connected Voiceflow account. Review the exact oo connector action and payload before approving write operations, and keep in mind that setup may require installing and signing into the OOMOL CLI.

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
94% confidence
Finding
The skill description says to use this skill for ANY Voiceflow request and instead of calling the API directly, which creates an overly broad routing trigger. In an agent environment, this can cause unintended invocation for loosely related Voiceflow tasks and may bypass more specific workflows, increasing the chance of unnecessary data access or accidental state-changing operations through the connector.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.