AgentPod is building a private, secure device for your AI agent.The AgentPod device is coming.Coming soonBe first
We checked this and rejected itprivacy

WhatsApp Web MCP Server: why it is not safe to use

Review warning: this skill can send WhatsApp data to webhooks, fetch remote media, and stores session auth data with broad account access.

What we found

Our review did not find hidden instructions, hardcoded secrets, obfuscated code, privilege escalation behavior, or destructive command flows in the inspected repository. The warning is based on how the skill handles account data and network access.

The server can forward incoming WhatsApp messages to a user-configured webhook. If enabled, those outbound payloads can include the sender number, sender name, message body, timestamp, and message ID, which means message data may leave the local environment. It can also fetch remote media at runtime when sending media from `http` or `https` URLs, and it posts incoming message payloads to the configured webhook endpoint.

We also found that it stores WhatsApp session authentication data locally, persists an API key in the auth data directory, and provides access to private chats, contacts, groups, and media from the connected WhatsApp account.

What to do instead

Use this skill only if you are comfortable with webhook forwarding and remote media fetches. Prefer setups that keep processing local, avoid enabling webhooks unless necessary, limit where outbound requests can go, and protect the local auth data directory and any connected account used with the skill.

Want the same outcome, safely? Use our checked skill instead.

Source: https://github.com/pnizer/wweb-mcp

We report what our security review found at the time we checked, with the goal of keeping people safe. Projects change; if a maintainer has since fixed this, we are glad to recheck it. Email hello@agentpod.com.

Copied to clipboard. Paste it into your AI (ChatGPT, Claude, or your agent) to add the skill.