audit_external_permissions
AI agents call audit_external_permissions to retrieve information from GAM MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'audit_' prefix strongly suggests a read/query operation, consistent with sibling tools like audit_all_permissions, audit_public_files, etc., which are all audit/reporting tools. It likely retrieves external sharing permission data. However, the empty description lowers confidence. Severity is medium because permission data in a Google Workspace environment is sensitive.
From the tool's definition Tool name 'audit_external_permissions' and server context (Google Workspace administrative actions). Description is empty.
Attacks that exploit this kind of access
audit_external_permissions. It is categorised as a Read tool in the GAM MCP Server MCP Server, which means it retrieves data without modifying state.
Register the GAM MCP Server MCP server in PolicyLayer and add a rule for audit_external_permissions: 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 GAM MCP Server. Nothing to install.
audit_external_permissions 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_external_permissions 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_external_permissions. 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_external_permissions is provided by the GAM MCP Server MCP server (ktibbs9417/gamcp). 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 →