Execute a command in a terminal session Use when native Bash is wrong because you need a persistent terminal session across turns/agents with output capture and replay. For one-shot shell commands, native Bash is fine.
AI agents invoke terminal_execute to trigger actions in Claude Flow. 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 executes arbitrary terminal commands in a persistent session, which is the definition of Execute category. The ability to run any command with cross-agent state persistence poses critical risk: an AI agent could execute destructive commands (rm -rf), exfiltrate data, install malware, modify system configuration, or pivot to other systems.
From the tool's definition Tool name is 'terminal_execute' and description states 'Execute a command in a terminal session' with 'output capture and replay' capabilities across turns and agents.
Attacks that exploit this kind of access
Execute a command in a terminal session Use when native Bash is wrong because you need a persistent terminal session across turns/agents with output capture and replay. For one-shot shell commands, native Bash is fine. It is categorised as a Execute tool in the Claude Flow MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Claude Flow MCP server in PolicyLayer and add a rule for terminal_execute: 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 Claude Flow. Nothing to install.
terminal_execute 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 terminal_execute 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 terminal_execute. 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.
terminal_execute is provided by the Claude Flow MCP server (claude-flow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.