pwndbg_plist
AI agents invoke pwndbg_plist to trigger actions in Pwndbg Lldb. 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.
The description is empty, so the classification relies on context. This tool is part of a pwndbg/LLDB MCP server designed for binary analysis and exploit development. The 'plist' suffix likely refers to listing something (possibly a process list or plist data structure), which could be a Read operation.
From the tool's definition Tool name is 'pwndbg_plist' on a server described as exposing pwndbg commands under LLDB for binary analysis and exploit development.
Attacks that exploit this kind of access
pwndbg_plist. It is categorised as a Execute tool in the Pwndbg Lldb MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Pwndbg Lldb MCP server in PolicyLayer and add a rule for pwndbg_plist: 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_plist 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 pwndbg_plist 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_plist. 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_plist 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 →