ClawHub
Back to skill

Security audit

ClickSend

Security checks across malware telemetry and agentic risk

Overview

This skill is a clearly disclosed ClickSend connector that can read and change ClickSend data, but its risky actions are labeled and require user confirmation.

Install only if you want your agent to operate ClickSend through OOMOL. Review SMS sends, contact updates, and deletes carefully before approval because they can cost money, message real recipients, or remove business data. Treat the remote oo CLI installer as a normal third-party setup step and use it only if you trust OOMOL.

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 (1)

Vague Triggers

Medium
Confidence
87% confidence
Finding
The skill description says to use this skill for ANY ClickSend request and whenever a task involves ClickSend, which is an overly broad trigger. That can cause the agent to route all ClickSend-related tasks through a shell-backed skill, including sensitive write or destructive operations, increasing the chance of unintended invocation and unnecessary exposure to command execution paths.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.