Group tenant-wide anomalous network-call detections by the calling process. Goal: spot VPN / mesh-networking daemons (tailscaled, twingate, zerotier-one, netbird, cloudflared, warp-svc, openvpn, wireguard) that are legitimately fanning out to many peer IPs and coordination endpoints as normal ope...
AI agents call analyze_anomalous_calls_by_process to retrieve information from Stepsecurity without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Even though analyze_anomalous_calls_by_process only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
Group tenant-wide anomalous network-call detections by the calling process. Goal: spot VPN / mesh-networking daemons (tailscaled, twingate, zerotier-one, netbird, cloudflared, warp-svc, openvpn, wireguard) that are legitimately fanning out to many peer IPs and coordination endpoints as normal operation. For those, a single process-scoped rule suppresses both domain AND direct-IP benign anomalies with one rule. Returns per-process: count, distinct endpoints, distinct direct IPs, sample detections (with dashboard links), and a suggested single suppression rule. When a VPN process appears (is_vpn_process_candidate=true), propose a process-wide rule (just {process: <name>, owner:. It is categorised as a Read tool in the Stepsecurity MCP Server, which means it retrieves data without modifying state.
Register the Stepsecurity MCP server in PolicyLayer and add a rule for analyze_anomalous_calls_by_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 Stepsecurity. Nothing to install.
analyze_anomalous_calls_by_process 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 analyze_anomalous_calls_by_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 analyze_anomalous_calls_by_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.
analyze_anomalous_calls_by_process is provided by the Stepsecurity MCP server (step-security/stepsecurity-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.