Load an executable file into GDB and set up PTY for process I/O.
AI agents invoke load_executable to trigger actions in Pwndbg. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool loads an arbitrary binary into GDB, a full-featured debugger, and sets up I/O infrastructure. It enables subsequent execution and control of arbitrary ELF binaries, which is a significant execution capability. Misuse could involve loading and running malicious or unintended binaries on the host system.
From the tool's definition Load an executable file into GDB and set up PTY for process I/O
Documented attack patterns abuse exactly the kind of access load_executable gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Pwndbg, and nothing reaches the server without passing your rules. This is the rule we recommend for load_executable:
{
"version": "1",
"default": "deny",
"tools": {
"load_executable": {
"limits": [
{
"counter": "load_executable_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}load_executable stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Load an executable file into GDB and set up PTY for process I/O. It is categorised as a Execute tool in the Pwndbg MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Pwndbg MCP server in PolicyLayer and add a rule for load_executable: 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. Nothing to install.
load_executable is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the load_executable 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 load_executable. 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.
load_executable is provided by the Pwndbg MCP server (rocketmadev/pwndbg-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 17 Pwndbg tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
17 Pwndbg tools catalogued and risk-classified — across an index of 42,500+ MCP servers.