AI agents call check_command_exists to retrieve information from Sysprobe without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves system information (whether a command exists and its location) without modifying, executing, or deleting anything. It is purely diagnostic and poses minimal risk if misused by an agent—the worst outcome would be incorrect path information, not system compromise.
From the tool's definition Tool checks for presence and returns absolute path of a CLI tool—a read-only query with no side effects. The verb 'check' and the return pattern ('presence + absolute path') indicate information retrieval only.
Attacks that exploit this kind of access
Is a CLI tool installed? Returns presence + absolute path. It is categorised as a Read tool in the Sysprobe MCP Server, which means it retrieves data without modifying state.
Register the Sysprobe MCP server in PolicyLayer and add a rule for check_command_exists: 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 Sysprobe. Nothing to install.
check_command_exists 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_command_exists 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_command_exists. 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_command_exists is provided by the Sysprobe MCP server (raindancer118/sysprobe-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 →