AI agents invoke kill_process to trigger actions in Sysprobe. 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.
Sending signals to processes is an Execute-level action: it directly controls running processes and can terminate them. While process termination could be considered destructive, processes can be restarted, and the primary action is triggering an OS-level signal rather than irreversibly destroying data. The default SIGTERM is graceful, though SIGKILL is possible.
From the tool's definition 'Send a signal to a PID' and '[ACTION] ... Gated' — this tool sends Unix signals (e.g., SIGTERM, SIGKILL) to running processes, which can terminate or alter process execution
Attacks that exploit this kind of access
[ACTION] Send a signal to a PID (default SIGTERM). Gated. It is categorised as a Execute tool in the Sysprobe MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Sysprobe MCP server in PolicyLayer and add a rule for kill_process: 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 Sysprobe. Nothing to install.
kill_process 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 kill_process 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 kill_process. 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.
kill_process is provided by the Sysprobe MCP server (raindancer118/sysprobe-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 →