Execute a shell command. On Windows uses pwsh; otherwise bash.
AI agents invoke run_shell to trigger actions in Copilot Studio Code. 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.
Shell command execution is inherently dangerous because it can trigger arbitrary side effects depending on agent arguments: system modifications, data exfiltration, malware installation, lateral movement, or resource consumption.
From the tool's definition Tool explicitly executes shell commands ('Execute a shell command') with platform-specific shells (pwsh on Windows, bash otherwise). No restrictions mentioned on command types or outputs.
Documented attack patterns abuse exactly the kind of access run_shell gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Copilot Studio Code, and nothing reaches the server without passing your rules. This is the rule we recommend for run_shell:
{
"version": "1",
"default": "deny",
"tools": {
"run_shell": {
"limits": [
{
"counter": "run_shell_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run_shell stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Execute a shell command. On Windows uses pwsh; otherwise bash. It is categorised as a Execute tool in the Copilot Studio Code MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Copilot Studio Code MCP server in PolicyLayer and add a rule for run_shell: 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 Copilot Studio Code. Nothing to install.
run_shell 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 run_shell 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 run_shell. 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.
run_shell is provided by the Copilot Studio Code MCP server (taiki-yoshida/copilot-studio-code). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Copilot Studio Code, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
7 Copilot Studio Code tools catalogued and risk-classified — across an index of 43,000+ MCP servers.