Get detailed information about a stack frame (LLDB native).
AI agents call pwndbg_frame_info 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.
This tool retrieves and displays stack frame metadata (variables, function context, addresses, etc.) without modifying program state or executing code. While the overall server context involves binary analysis and reverse engineering on live processes, this specific tool is read-only.
From the tool's definition Tool description states 'Get detailed information about a stack frame' which is a retrieval/inspection operation with no modification capability. The 'LLDB native' designation confirms it is a passive debugging query.
Attacks that exploit this kind of access
Get detailed information about a stack frame (LLDB native). 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_frame_info: 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_frame_info 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_frame_info 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_frame_info. 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_frame_info 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 →