ClawHub
Back to skill

Security audit

Sats4AI

Security checks across malware telemetry and agentic risk

Overview

The skill appears to expose SMS-sending capability without clearly warning users about real-world message delivery, costs, or privacy impact.

Review the skill documentation before installing and only use SMS sending when you explicitly intend to contact the recipient. Confirm what provider is used, where phone numbers and message bodies are sent, whether charges apply, and whether the agent asks for confirmation before sending.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill advertises a send_sms capability but provides no warning that message contents and destination phone numbers will be transmitted to an external service, may incur per-message charges, and may create privacy, compliance, or abuse risks. In an agent context, a user may not realize that invoking this tool can contact third parties in the real world, making the omission materially dangerous even if the capability is legitimate.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal