AI agents call check_security to retrieve information from Mcp Ssh without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'check_' prefix combined with security context implies verification or audit of security status rather than enforcement changes. No evidence of side effects, destructive operations, code execution triggers, or financial impact. Classified as Read with moderate confidence due to missing description; if it performed active hardening or executed security tools, severity might escalate to medium/high.
From the tool's definition Tool name 'check_security' suggests a read-only inspection operation. Server context emphasizes 'monitoring' and 'diagnostics' alongside command execution.
Attacks that exploit this kind of access
check_security. It is categorised as a Read tool in the Mcp Ssh MCP Server, which means it retrieves data without modifying state.
Register the Mcp Ssh MCP server in PolicyLayer and add a rule for check_security: 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 Mcp Ssh. Nothing to install.
check_security 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 check_security 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 check_security. 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.
check_security is provided by the Mcp Ssh MCP server (zhouxiangjing/mcp-ssh). 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 →