pwndbg_probeleak
AI agents call pwndbg_probeleak 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.
The description is empty, so classification is based solely on the tool name. 'probeleak' in pwndbg typically refers to scanning memory for potential information leaks (pointer leaks, etc.), which is a read/analysis operation. Given the server context (binary analysis, exploit development), this is likely reading memory. Confidence is lowered due to the empty description.
From the tool's definition Tool name 'pwndbg_probeleak' — 'probe' suggests scanning/reading memory regions for leak detection, which is a read operation in a debugger context.
Attacks that exploit this kind of access
pwndbg_probeleak. 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_probeleak: 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_probeleak 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_probeleak 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_probeleak. 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_probeleak 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 →