AI agents invoke open_attachment to trigger actions in Eml. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool triggers execution of an external application on the host system to open a file. The specific application launched depends on the file type and system configuration, meaning an attacker could potentially cause arbitrary executables to be launched if a malicious attachment is present. This goes beyond a simple read operation — it invokes system-level execution.
From the tool's definition 'Open an attachment with the system default application'
Attacks that exploit this kind of access
Open an attachment with the system default application. It is categorised as a Execute tool in the Eml MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Eml MCP server in PolicyLayer and add a rule for open_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 Eml. Nothing to install.
open_attachment is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the open_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 open_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.
open_attachment is provided by the Eml MCP server (miguelripoll23/eml-mcp). 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 →