Load a core dump file for post-mortem analysis.
AI agents call pwndbg_load_core to retrieve information from Pwndbg Lldb without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Loading a core dump file is an inspection and data retrieval operation that examines a snapshot of process state at the time of a crash. While the server exposes pwndbg (an advanced debugger) used for binary analysis and exploit development, the specific act of loading a core dump file itself is a read operation—it accesses existing post-mortem data without side effects on the running system or the core file itself.
From the tool's definition Tool loads a core dump file for analysis without modifying or executing code. Core dump analysis is inherently a read-only forensic operation.
Attacks that exploit this kind of access
Load a core dump file for post-mortem analysis. It is categorised as a Read tool in the Pwndbg Lldb MCP Server, which means it retrieves data without modifying state.
Register the Pwndbg Lldb MCP server in PolicyLayer and add a rule for pwndbg_load_core: 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_load_core 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 pwndbg_load_core 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_load_core. 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_load_core 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 →