Security audit
Security checks for vulnerabilities and agentic risk
This WhatsApp automation skill describes powerful messaging, group-management, chat-search, callback, and command-execution abilities, but its scope and credential guidance are inconsistent and under-controlled.
Review carefully before installing. Use it only for explicit WhatsApp tasks, confirm recipients and group changes before execution, avoid sensitive chat searches unless necessary, and do not provide credentials until the publisher clarifies the missing script and API-key requirements.
The invocation guidance is overly broad, telling agents to use the skill for generic efficiency, automation, batch processing, and workflow optimization. Because the skill can send messages, search history, manage groups, and execute commands, broad triggers increase the chance of accidental activation for unrelated user requests with privacy or real-world action consequences.
The manifest/license text mixes unrelated SEO-use language into a WhatsApp messaging skill, creating scope confusion about what the skill is supposed to do. This can mislead routing, review, or approval processes and may cause the skill to be invoked in contexts involving unrelated data or actions, increasing the risk of unsafe execution.
The manifest includes conflicting use conditions, including unrelated SEO scenarios, which reduces trigger specificity and makes tool selection unreliable. In an agent ecosystem, this ambiguity can cause the messaging skill to be chosen for the wrong task, exposing chat data or causing unintended outbound actions.
The skill describes capabilities with significant privacy and external-action impact—message sending, history search, group management, callback URLs, and network behavior—without strong user-facing warnings or consent requirements. In this context, the absence of prominent safeguards makes accidental disclosure, unauthorized messaging, and misuse of sensitive chat data materially more likely.
The documentation contradicts itself on whether an API key is required, which can cause operators to misconfigure authentication, rely on implicit credentials, or handle secrets unsafely. In a skill with networked messaging and exec capability, configuration ambiguity increases the chance of insecure deployment and accidental credential exposure.
No suspicious patterns detected.
