ClawHub

Lets Enhance

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Let's Enhance integration that uses Membrane for account connection and media API actions, with no evidence of hidden or destructive behavior.

Install only if you trust Membrane and are comfortable connecting it to your Let's Enhance account. Prefer the listed actions, and confirm before sending private images, videos, metadata, or using raw proxy requests that create, modify, or delete account data.

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
89% confidence
Finding
The skill description is broad enough that it could be invoked for vague requests like 'enhance this image' or 'manage my images,' causing an agent to engage the skill without sufficiently confirming user intent, scope, or what data will be sent to an external service. In a network-enabled integration skill, over-broad triggering increases the chance of unintended external actions or data disclosure.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill explicitly instructs agents to send direct proxy requests to the external API, but it does not require a user-facing warning or confirmation that image or video data may be transmitted to a third-party service. For media-processing workflows, this omission can lead to accidental sharing of sensitive files or metadata with an external provider.

VirusTotal

58/58 vendors flagged this skill as clean.

View on VirusTotal