AI agents use send_image_message to create or update resources in Whatsapp — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Whatsapp environment.
The tool sends (creates) an image message to WhatsApp contacts. While the message itself is reversible in theory (can be deleted later), the send action is a write operation with observable side effects: it transmits data to recipients and creates persistent records. The blast radius is medium—a misused tool could spam users, send inappropriate images, or leak sensitive media to wrong recipients.
From the tool's definition Tool description states 'Send an image' which creates and transmits a message object. This is a write operation that modifies conversation state by adding a new message artifact.
Attacks that exploit this kind of access
Send an image via URL or media ID. Supports caption. It is categorised as a Write tool in the Whatsapp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Whatsapp MCP server in PolicyLayer and add a rule for send_image_message: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Whatsapp. Nothing to install.
send_image_message is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the send_image_message rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for send_image_message. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
send_image_message is provided by the Whatsapp MCP server (spirit122/whatsapp-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →