ClawHub

Unifiedto

Security checks across malware telemetry and agentic risk

Overview

This appears to be a legitimate Unified.to/Membrane integration, but it gives an agent broad authenticated ability to change connected SaaS data without built-in approval safeguards.

Install only if you trust Membrane and Unified.to with the connected accounts. Use least-privilege scopes, prefer discovered Membrane actions over raw proxy requests, require explicit approval before creates, updates, deletes, workflow automation, or raw API calls, and revoke unused connections when finished.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
82% confidence
Finding
The skill description is broad enough to match many generic requests about interacting with data or automating workflows, which can cause the agent to invoke this integration in contexts the user did not specifically intend. Because this skill can connect to external SaaS systems and perform actions against live data, over-broad routing increases the chance of unintended access or operations.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill explicitly supports direct proxy requests with GET, POST, PUT, PATCH, and DELETE, but it does not require confirmation, dry-run behavior, or even a warning before mutating live external systems. In an agent setting, this creates a real risk of accidental data modification, deletion, or workflow execution across connected third-party applications.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal