ClawHub
Back to skill

Security audit

WhatsAble

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed WhatsAble connector helper with a write action that requires user confirmation before sending messages.

Before installing, be aware that this can send WhatsApp messages through your connected WhatsAble account. Confirm recipient, message body, attachment URL, and intended effect before allowing any send_message run, and only complete OOMOL login or connection setup when you intend to use the integration.

SkillSpector

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
93% confidence
Finding
The skill description says to use this skill for ANY WhatsAble request and whenever a task involves WhatsAble, which is an overly broad trigger that can cause the agent to invoke the skill on casual mentions rather than clear user intent. Because this skill includes a write-capable action (`send_message`), over-triggering increases the chance of unintended external actions or unnecessary schema/connector calls in response to ambiguous prompts.

Static analysis

No suspicious patterns detected.