Clean a project directory to prepare for rebuilding.
AI agents call clean_project to retrieve information from APK Security Guard MCP Suite without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Even though clean_project 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
Clean a project directory to prepare for rebuilding. It is categorised as a Read tool in the APK Security Guard MCP Suite MCP Server, which means it retrieves data without modifying state.
Register the APK Security Guard MCP Suite MCP server in PolicyLayer and add a rule for clean_project: 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 APK Security Guard MCP Suite. Nothing to install.
clean_project 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 clean_project 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 clean_project. 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.
clean_project is provided by the APK Security Guard MCP Suite MCP server (zmbcen/apk-security-guard-mcp-suite). 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 →