pwndbg_bins
AI agents call pwndbg_bins 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.
Based on pwndbg command naming conventions, 'bins' likely retrieves information about binary segments, memory regions, or mapped binaries—a read-only operation with no side effects. However, empty description and potential for indirect information disclosure (memory layout leaks useful for exploit development) justify medium severity rather than low. Confidence reduced due to lack of explicit documentation.
From the tool's definition Tool name 'pwndbg_bins' with empty description; 'bins' in pwndbg context typically queries binary/memory layout information (read operation). Server context indicates binary analysis and debugging use cases.
Attacks that exploit this kind of access
pwndbg_bins. 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_bins: 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_bins 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_bins 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_bins. 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_bins 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 →