scan_output

Scan LLM output for data leakage, secrets, PII, and exfiltration patterns

Server ZugaShield zuga-technologies/zugashield
Category Read
Risk class Low
Parameters 00 required

What scan_output does on ZugaShield

AI agents call scan_output to retrieve information from ZugaShield without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why scan_output needs a policy

This is a security scanning/monitoring tool that reads and analyzes LLM output to detect sensitive data patterns. It has no side effects—it does not modify data, execute code, destroy resources, or commit financial transactions. The sole purpose is to inspect and report on output characteristics for security purposes, making it clearly a Read category tool.

From the tool's definition Tool name is 'scan_output' and description states it 'scan[s]' output for data leakage and patterns. The verb 'scan' indicates passive analysis and inspection; the tool retrieves and analyzes data without modifying, executing operations, deleting, or moving…

Questions about scan_output

What does the scan_output tool do? +

Scan LLM output for data leakage, secrets, PII, and exfiltration patterns. It is categorised as a Read tool in the ZugaShield MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on scan_output? +

Register the ZugaShield MCP server in PolicyLayer and add a rule for scan_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 ZugaShield. Nothing to install.

What risk level is scan_output? +

scan_output is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit scan_output? +

Yes. Add a rate_limit block to the scan_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.

How do I block scan_output completely? +

Set action: deny in the PolicyLayer policy for scan_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.

What MCP server provides scan_output? +

scan_output is provided by the ZugaShield MCP server (zuga-technologies/zugashield). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// THE FULL RECORD

scan_output is one line of ZugaShield's registry record.

The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.