删除远程文件或目录
AI agents call ssh_remove_remote_file to permanently remove resources in Ssh Agent — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently deletes files or directories on a remote system via SSH. Deletion is irreversible and cannot be undone, fitting the Destructive category. The high severity reflects the potential for significant data loss if an AI agent is tricked into removing critical files.
From the tool's definition Tool name 'ssh_remove_remote_file' combined with description '删除远程文件或目录' (delete remote file or directory). The verb 'remove' / '删除' (delete) indicates irreversible data destruction.
Attacks that exploit this kind of access
删除远程文件或目录. It is categorised as a Destructive tool in the Ssh Agent MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Ssh Agent MCP server in PolicyLayer and add a rule for ssh_remove_remote_file: 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_remove_remote_file is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the ssh_remove_remote_file 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_remove_remote_file. 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_remove_remote_file 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 →