List sandboxes created as git worktrees under .sandboxes.
AI agents call sandbox_list to retrieve information from Promethean OS MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about existing sandboxes without creating, modifying, deleting, or executing anything. It is a pure read operation that queries the file system for metadata about git worktrees. The blast radius is minimal since it only surfaces existing sandbox information.
From the tool's definition Tool name is 'sandbox_list' and description states it 'List sandboxes' — a query/retrieval operation with no modification or execution. The operation reads the state of git worktrees in the .sandboxes directory.
Attacks that exploit this kind of access
List sandboxes created as git worktrees under .sandboxes. It is categorised as a Read tool in the Promethean OS MCP MCP Server, which means it retrieves data without modifying state.
Register the Promethean OS MCP server in PolicyLayer and add a rule for sandbox_list: 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 Promethean OS MCP. Nothing to install.
sandbox_list 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 sandbox_list 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 sandbox_list. 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.
sandbox_list is provided by the Promethean OS MCP server (octave-commons/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 →