🔍 スクリプトプロパティのセキュリティ監査を実行します
AI agents call audit_properties to retrieve information from Google Apps Script MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
A security audit of script properties is fundamentally a read/inspect operation: it retrieves stored properties and evaluates them for security issues. No modification, deletion, or execution of code is implied. Severity is medium because script properties often contain secrets/credentials, so reading them carries meaningful risk if misused, but the tool itself does not alter or expose data beyond the audit report.
From the tool's definition audit_properties — '監査を実行します' means 'performs an audit'; auditing typically reads and inspects configuration/property data without modifying it
Attacks that exploit this kind of access
🔍 スクリプトプロパティのセキュリティ監査を実行します. It is categorised as a Read tool in the Google Apps Script MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Google Apps Script MCP Server MCP server in PolicyLayer and add a rule for audit_properties: 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 Google Apps Script MCP Server. Nothing to install.
audit_properties 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 audit_properties 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 audit_properties. 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.
audit_properties is provided by the Google Apps Script MCP Server MCP server (utakata/google-apps-script-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 →