AI agents call shell_get_output to retrieve information from LocalAnt without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves process output that has already been captured from a background process. It does not execute commands, modify data, delete anything, or trigger financial operations. While it operates in the context of shell process management, the specific action is read-only retrieval of cached/stored output.
From the tool's definition Tool name 'shell_get_output' and description 'Get captured stdout/stderr/status for a tracked background process' indicate retrieval of process output data with no modification or execution of new commands.
Attacks that exploit this kind of access
Get captured stdout/stderr/status for a tracked background process. It is categorised as a Read tool in the LocalAnt MCP Server, which means it retrieves data without modifying state.
Register the LocalAnt MCP server in PolicyLayer and add a rule for shell_get_output: 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 LocalAnt. Nothing to install.
shell_get_output 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 shell_get_output 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 shell_get_output. 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.
shell_get_output is provided by the LocalAnt MCP server (yuga-hashimoto/localant). 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 →