ClawHub
Back to skill

Security audit

Whatsapp Msg Tool Free

Security checks across malware telemetry and agentic risk

Overview

This WhatsApp skill mostly matches its stated messaging purpose, but it includes unrelated trigger keywords that could invoke message or chat-search authority in the wrong context.

Install only if you want an agent to operate WhatsApp through a local CLI. Before use, confirm every recipient, message, file path, and chat search explicitly, and protect ~/.wacli/ because it contains account-equivalent session data. Be cautious because the skill’s trigger wording includes unrelated SEO terms that should be narrowed by the publisher.

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
93% confidence
Finding
The capability-scope keyword list is excessively broad and includes unrelated terms such as SEO, ranking improvement, and search-traffic optimization, which do not match the stated WhatsApp messaging purpose. This can cause the agent platform to invoke the skill for unrelated requests, increasing the chance of unintended message sending, file transmission, or chat-history access in the wrong context.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill enables sending third-party messages, transferring files, searching message history, and storing local credentials and chat data, but it does not present an upfront privacy and data-handling warning before these capabilities are introduced. In practice, this reduces user awareness around sensitive actions involving personal contacts, message contents, local credential persistence, and searchable historical communications.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.