ClawHub

Verimor SMS

Security checks across malware telemetry and agentic risk

Overview

This skill matches its Verimor SMS purpose, but it can send paid messages and change campaign or blacklist state without strong confirmation safeguards.

Install only if you want an agent to operate a real Verimor SMS account. Use restricted or dedicated credentials where possible, and require manual confirmation for every send, cancellation, or blacklist change, especially for bulk recipients, commercial messages, or scheduled campaigns.

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 (2)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The SMS-send activation phrases are broad enough to match ordinary conversational requests, which can cause the agent to trigger a real-world outbound action without sufficiently explicit user intent. In this skill, that means sending paid messages to external recipients, creating both financial cost and abuse risk if the agent misinterprets casual language.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The campaign-cancel operation is a destructive state-changing action, but the skill provides no warning, preview, or confirmation before executing it. A mistaken interpretation, wrong campaign ID, or prompt injection through conversation context could cancel scheduled outbound communications and disrupt business operations.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal