Delete capture files from the captures directory
AI agents call cleanup_captures to permanently remove resources in Sec Aircrack Ng — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes capture files without possibility of recovery. Although the context is authorized WiFi security assessments, deletion of data is irreversible and could be misused to destroy evidence or legitimate security test results.
From the tool's definition Tool name is 'cleanup_captures' with description 'Delete capture files from the captures directory'—the verb 'Delete' and the intent to remove files from disk are explicit and irreversible.
Attacks that exploit this kind of access
Delete capture files from the captures directory. It is categorised as a Destructive tool in the Sec Aircrack Ng MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Sec Aircrack Ng MCP server in PolicyLayer and add a rule for cleanup_captures: 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 Sec Aircrack Ng. Nothing to install.
cleanup_captures is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the cleanup_captures 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 cleanup_captures. 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.
cleanup_captures is provided by the Sec Aircrack Ng MCP server (schwarztim/sec-aircrack-ng-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 →