Scan user input for prompt injection, encoding attacks, and other threats
AI agents call scan_input 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.
scan_input performs threat detection by examining user input for malicious patterns (prompt injection, encoding attacks). This is a read-only operation that queries/analyzes data without side effects, making it a Read category tool.
From the tool's definition Tool description states it 'scan[s]' input for threats, indicating inspection and analysis without modification or execution. No language suggesting write, execute, destructive, or financial operations.
Attacks that exploit this kind of access
Scan user input for prompt injection, encoding attacks, and other threats. It is categorised as a Read tool in the ZugaShield MCP Server, which means it retrieves data without modifying state.
Register the ZugaShield MCP server in PolicyLayer and add a rule for scan_input: 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.
scan_input 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 scan_input 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 scan_input. 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.
scan_input 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.
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 →