Delete a breakpoint by its ID number.
AI agents call pwndbg_breakpoint_delete to permanently remove resources in Pwndbg Lldb — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting a breakpoint is an irreversible action within the debugging session; the breakpoint configuration is permanently removed and cannot be recovered. While the blast radius is limited to the debugging session (not production data), it qualifies as Destructive because the action cannot be undone without recreating the breakpoint manually.
From the tool's definition 'Delete a breakpoint by its ID number' — permanently removes a debugging breakpoint configuration
Attacks that exploit this kind of access
Delete a breakpoint by its ID number. It is categorised as a Destructive tool in the Pwndbg Lldb MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Pwndbg Lldb MCP server in PolicyLayer and add a rule for pwndbg_breakpoint_delete: 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 Pwndbg Lldb. Nothing to install.
pwndbg_breakpoint_delete 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 pwndbg_breakpoint_delete 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 pwndbg_breakpoint_delete. 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.
pwndbg_breakpoint_delete is provided by the Pwndbg Lldb MCP server (micro-evaluation-group/pwndbg-lldb-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 →