AI agents call mail_download_attachment to retrieve information from Outpost without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and returns existing email attachment data without creating, modifying, or deleting anything. It has no side effects beyond data retrieval. While attachments could theoretically contain sensitive information, the tool itself performs only a read operation with no destructive or modifying capabilities.
From the tool's definition Tool description states 'Download an email attachment. Returns filename and base64-encoded content.' The verb 'Download' and the retrieval-only nature of returning existing attachment data without modification indicates a read operation.
Attacks that exploit this kind of access
Download an email attachment. Returns filename and base64-encoded content. It is categorised as a Read tool in the Outpost MCP Server, which means it retrieves data without modifying state.
Register the Outpost MCP server in PolicyLayer and add a rule for mail_download_attachment: 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 Outpost. Nothing to install.
mail_download_attachment is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the mail_download_attachment 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 mail_download_attachment. 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.
mail_download_attachment is provided by the Outpost MCP server (signalclaude/outpost). 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 →