scan_terminal_security
Scan project files and dev environment for terminal security threats: Unicode homograph attacks, ANSI escape injections, invisible characters, and suspicious URL patterns. Auto-discovers dotfiles, CI configs, env files, shell scripts, and package manifests. Inspired by github.com/HomenShum/termin...
This record as markdown: /tools/io-github-homenshum-nodebench/scan-terminal-security.md
What scan_terminal_security does on Nodebench
AI agents call scan_terminal_security to retrieve information from Nodebench without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why scan_terminal_security is rated Low
This tool retrieves and analyzes data from files to identify potential security threats. It does not create, modify, delete, or execute code. It does not move money or trigger external operations based on findings. The scanning activity is purely informational—examining dotfiles, CI configs, env files, shell scripts, and package manifests to report on existing security issues.
From the tool's definition The tool 'scan_terminal_security' performs security scanning and threat detection across project files and dev environment configurations. It 'scans' and 'auto-discovers' existing files without modifying, deleting, or executing them.
Attacks that exploit this kind of access
The rule that runs scan_terminal_security safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Nodebench, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For scan_terminal_security, this is the rule to start with:
scan_terminal_security is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Nodebench, apply this rule, and every scan_terminal_security call is checked against it from then on.
Questions about scan_terminal_security
Scan project files and dev environment for terminal security threats: Unicode homograph attacks, ANSI escape injections, invisible characters, and suspicious URL patterns. Auto-discovers dotfiles, CI configs, env files, shell scripts, and package manifests. Inspired by github.com/HomenShum/terminal-security-scanner. It is categorised as a Read tool in the Nodebench MCP Server, which means it retrieves data without modifying state.
Register the Nodebench MCP server in PolicyLayer and add a rule for scan_terminal_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 Nodebench. Nothing to install.
scan_terminal_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 scan_terminal_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 scan_terminal_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.
scan_terminal_security is provided by the Nodebench MCP server (nodebench-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Nodebench, and thousands of servers like it.
This server
Across the catalogue