Security audit

Whatsapp Master Free

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed WhatsApp messaging helper with broad but purpose-aligned agent tool needs and no embedded executable payloads.

Install only if you are comfortable linking a WhatsApp account to the agent platform. Review each recipient, message body, and media path before sending, avoid unsolicited or bulk messaging, and remember that the WhatsApp login session may persist in the platform.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: This skill enables sending WhatsApp messages and media through an agent with exec capability, but the early descriptive sections do not prominently warn about privacy exposure, spam policy violations, or account suspension risk. In this context, under-warning is security-relevant because users may automate messaging against personal contacts or customer data without informed consent or safeguards.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The manifest repeatedly states that free edition capabilities are limited to sending messages and explicitly marks '历史搜索' and related advanced functions as professional-only. However, the generic capability text says the core execution supports '创建/查询/导出操作', which directly suggests search/export behavior inconsistent with the stated free-version scope.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The skill is described as a WhatsApp messaging wrapper with limited free-version functionality, but this line documents a configuration interface supporting '修改/重置/导入操作'. That contradicts the narrow messaging-focused intent and reads like boilerplate for broader stateful management features not otherwise described for this skill.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 80% confidence
Finding: The description is written primarily in Chinese and includes embedded English phrasing, but nowhere offers users a language or locale choice. This can be a language policy concern if organizational policy requires user opt-in before forcing a specific language or locale in skill instructions.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The manifest and feature matrix position this skill as a sender of WhatsApp text/media/stickers/voice/GIF, not a general export or persistence tool. Saying result handling supports '导出/保存/转换操作' overstates or contradicts the intended scope and appears copied from a generic template rather than matching the actual skill intent.
Content: No source excerpt is available for this finding.