AI agents call shell_get_process_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 data (process output) that has already been captured. It performs a query/fetch operation with no side effects on the system state. The blast radius is minimal—misuse could leak sensitive information from process logs, warranting 'low' severity rather than negligible, but the operation itself is non-destructive and read-only.
From the tool's definition Tool name 'shell_get_process_output' and description 'Get captured output of a tracked process' indicate a read operation that retrieves previously captured output from an already-running process. No execution, modification, or deletion occurs.
Attacks that exploit this kind of access
Get captured output of a tracked 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_process_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_process_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_process_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_process_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_process_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 →