ClawHub

Labsmobile

Security checks across malware telemetry and agentic risk

Overview

This is a coherent LabsMobile integration, but it gives an agent chargeable outbound SMS and broad authenticated API power without clear confirmation guardrails.

Install only if you trust Membrane and intend to let an agent operate your LabsMobile account. Before any SMS send, bulk send, scheduled-message change, contact or group change, or raw proxy request, require the agent to show the exact recipients, message body, action, and likely account or cost impact, then get explicit approval.

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
86% confidence
Finding
The skill description and invocation guidance are broad enough that an agent may select this skill for loosely related requests involving contacts, messaging, or LabsMobile-adjacent tasks. Because the skill can trigger external actions such as sending SMS or managing groups, overbroad routing increases the chance of unintended real-world actions or data access from ambiguous prompts.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill enables high-impact external actions—sending SMS, bulk messaging, and raw API/proxy requests—without prominent user-facing warnings or consent language about message transmission, recipient impact, costs, or data sharing with a third party. In context, this is more dangerous because LabsMobile is an outbound communications platform and misuse can immediately affect real recipients, incur charges, or expose contact data.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal