AI agents call ssh_get_interactive_output 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.
The tool appears to read/retrieve buffered output from an existing interactive SSH session without executing new commands. However, the context of an SSH agent server means the session itself may be running arbitrary remote commands, so misuse could expose sensitive output. Severity is medium due to potential for leaking credentials or sensitive system information from an active session.
From the tool's definition 获取交互式会话的输出 translates to 'Get the output of an interactive session' — retrieves/reads output data
Attacks that exploit this kind of access
获取交互式会话的输出. 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_get_interactive_output: 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_get_interactive_output 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_get_interactive_output 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_get_interactive_output. 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_get_interactive_output 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.
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 →