AI agents call ssh_list_async_commands to retrieve information from Ssh Agent without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves the state of asynchronous commands without modifying or deleting data. It is a read operation. However, severity is elevated to medium because: (1) the SSH-agent context means it operates on remote systems where command execution may have sensitive side effects, and (2) listing command statuses could reveal information about what commands were executed, potentially exposing…
From the tool's definition Tool name 'ssh_list_async_commands' combined with description '列出所有异步命令状态' (list all asynchronous command statuses) indicates retrieval of status information about previously executed commands.
Attacks that exploit this kind of access
列出所有异步命令状态. It is categorised as a Read tool in the Ssh Agent MCP Server, which means it retrieves data without modifying state.
Register the Ssh Agent MCP server in PolicyLayer and add a rule for ssh_list_async_commands: 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 Ssh Agent. Nothing to install.
ssh_list_async_commands 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 ssh_list_async_commands 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 ssh_list_async_commands. 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.
ssh_list_async_commands is provided by the Ssh Agent MCP server (zhijun/ssh-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
ssh_list_async_commands is one line of Ssh Agent's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →