Security audit

Whatsapp Master Free

Security checks across malware telemetry and agentic risk

Overview

This WhatsApp messaging skill mostly matches its stated purpose, but it requests broad local execution and messaging authority with vague routing and limited send-confirmation guidance.

Review this skill before installing. Use it only for explicit WhatsApp send tasks, verify the recipient and any attached file before each send, and avoid allowing unsupervised ffmpeg or shell execution on untrusted paths or user-supplied filenames.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands

Findings (5)

Description-Behavior Mismatch

Medium

Confidence: 89% confidence
Finding: The skill documents generic create/query/export/import/save/convert operations that extend beyond its declared WhatsApp message-sending purpose. In an agent ecosystem, this kind of scope inflation can cause the skill to be selected for unrelated tasks and can enable unintended handling or transformation of user data, increasing the chance of misuse or over-privileged execution.

Context-Inappropriate Capability

Medium

Confidence: 84% confidence
Finding: Granting exec to a messaging skill broadens it from communications into arbitrary command execution, and the documentation explicitly encourages ffmpeg use through that channel. If the agent passes attacker-influenced file paths or shell fragments into exec, this can lead to command injection, unauthorized file access, or execution of unintended local commands.

Vague Triggers

Medium

Confidence: 86% confidence
Finding: The invocation guidance ties the skill to very broad activities like coding, debugging, testing, and deployment rather than narrowly to WhatsApp messaging tasks. In agent routing systems, this increases the probability that the skill is auto-invoked in contexts where external messaging, file handling, or exec access is unnecessary, creating avoidable exposure.

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The capability keyword list is excessively broad and includes fragmented and ambiguous phrases, which can cause accidental routing and overmatching. Because the skill can transmit data externally and has exec available, mistaken activation is more dangerous than for a read-only informational skill.

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The skill enables sending messages and media to external recipients without prominently warning that content may leave the local environment and be delivered to third parties. In an agent setting, this can result in unintended disclosure of sensitive text, files, or identifiers if users do not realize the action has real-world outbound effects.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.