AI agents call list_sandbox_specs to retrieve information from Swarm without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Even though list_sandbox_specs only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
List all saved sandbox specs from ~/.claude/sandboxes/. It is categorised as a Read tool in the Swarm MCP Server, which means it retrieves data without modifying state.
Register the Swarm MCP server in PolicyLayer and add a rule for list_sandbox_specs: 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 Swarm. Nothing to install.
list_sandbox_specs 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 list_sandbox_specs 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 list_sandbox_specs. 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.
list_sandbox_specs is provided by the Swarm MCP server (stiege/swarm-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.