# 36 terms for AI endpoint security, defined here with a sourced example on each term page

GLOSSARY, read 12 Nov 2026

**The short answer.** The glossary defines 36 terms used across the index, from agent inventory and shadow AI to MCP servers, prompt injection and endpoint detection and response. Each term has a plain definition and an example taken from a primary source, with the URL and the date it was read.

- [AI endpoint security](/glossary/ai-endpoint-security/): AI endpoint security is the practice of finding, governing and stopping the AI tools that run on employee devices.
- [Agentic endpoint](/glossary/agentic-endpoint/): An agentic endpoint is a laptop, workstation or developer machine where autonomous AI agents act with the user's access.
- [Coding agent](/glossary/coding-agent/): A coding agent is an AI tool that reads a repository, edits files, runs commands and calls tools to finish a development task with limited step-by-step direction.
- [Command-line agent](/glossary/command-line-agent/): A command-line agent is a coding agent that runs in a terminal session instead of an editor window.
- [MCP server (local stdio)](/glossary/mcp-server-local-stdio/): A local stdio MCP server is a program the MCP client launches as a subprocess on the same machine, talking over standard input and output.
- [MCP client](/glossary/mcp-client/): An MCP client is the connector inside an AI application that holds a dedicated connection to one MCP server.
- [Tool call](/glossary/tool-call/): A tool call is a request from the model, run through the client, to execute a named function on a server or in the agent itself, with arguments.
- [Agent skill](/glossary/agent-skill/): An agent skill is a packaged set of instructions, and sometimes scripts, that an agent loads when a task matches.
- [Plugin](/glossary/plugin/): In a coding agent, a plugin is a bundle that can contain skills, sub-agents, hooks and MCP servers, installed as one unit, usually from a marketplace.
- [Browser agent](/glossary/browser-agent/): A browser agent is an AI agent that navigates web pages, reads content, fills forms and clicks on behalf of a user.
- [Shadow AI](/glossary/shadow-ai/): Shadow AI is the use of AI tools that security and IT have not approved or cannot see.
- [AI DLP](/glossary/ai-dlp/): AI DLP is data loss prevention aimed at prompts, uploads and agent context sent to AI tools.
- [Data paste control](/glossary/data-paste-control/): A data paste control is a policy that inspects, warns on or blocks pasting content into AI tools, in a browser or a desktop app.
- [Agentless deployment](/glossary/agentless-deployment/): Agentless deployment means coverage that does not install a new persistent sensor on each device.
- [Endpoint agent](/glossary/endpoint-agent/): An endpoint agent is the software sensor installed on a device to collect telemetry and enforce policy.
- [Managed settings](/glossary/managed-settings/): Managed settings are configuration that an organization deploys to devices and that users cannot override.
- [Permission mode](/glossary/permission-mode/): A permission mode is a setting that decides how often an agent must ask before acting, from asking on every action to skipping prompts.
- [Allowlist](/glossary/allowlist/): An allowlist is a documented list of elements that policy permits, with everything else denied.
- [Sandbox](/glossary/sandbox/): A sandbox is a restricted, controlled execution environment that limits what software can reach, typically the file system and network.
- [Prompt injection](/glossary/prompt-injection/): Prompt injection is when input to a language model changes its behavior in ways its operator did not intend.
- [Indirect prompt injection](/glossary/indirect-prompt-injection/): Indirect prompt injection happens when the instructions come from content the agent reads, such as a web page, a file or a repository, instead of from the user.
- [Tool poisoning](/glossary/tool-poisoning/): Tool poisoning is hiding instructions in an MCP tool's description or metadata.
- [Slopsquatting / package hallucination](/glossary/slopsquatting-package-hallucination/): Package hallucination is when a model suggests a software package name that does not exist.
- [Credential exposure](/glossary/credential-exposure/): Credential exposure is when tokens, keys or passwords become readable to an agent, a tool or an attacker.
- [Secrets in context](/glossary/secrets-in-context/): Secrets in context are credentials or private data that have been loaded into an agent's context window.
- [EDR](/glossary/edr/): Endpoint detection and response is a security tool that continuously monitors devices, records system-level behavior, detects suspicious activity and helps respond.
- [Audit trail](/glossary/audit-trail/): An audit trail is a chronological record that lets you reconstruct the sequence of activities around an event.
- [Runtime guardrail](/glossary/runtime-guardrail/): A runtime guardrail is a control that inspects and can block an agent's prompts or actions while it runs, as opposed to scanning it before deployment.
- [Pre-execution block](/glossary/pre-execution-block/): A pre-execution block stops a tool call before it runs, based on policy, instead of detecting it afterward.
- [Inventory](/glossary/inventory/): An inventory is a current list of the AI tools, agents, MCP servers, skills and extensions on each device, with versions and owners.
- [Desktop AI app](/glossary/desktop-ai-app/): A desktop AI app is a native application, such as an AI chat client with local file access, that runs on the user's machine.
- [IDE extension marketplace](/glossary/ide-extension-marketplace/): An IDE extension marketplace is the catalog where editors such as VS Code and Cursor fetch extensions.
- [Rug pull (MCP)](/glossary/rug-pull-mcp/): In MCP, a rug pull is when a server changes a tool's description or behavior after the user approved it.
- [Least privilege for agents](/glossary/least-privilege-for-agents/): Least privilege for agents means giving an agent only the files, tools, network access and credentials its task needs, for as long as it needs them.
- [Human-in-the-loop approval](/glossary/human-in-the-loop-approval/): Human-in-the-loop approval requires a person to confirm an agent action before it runs.
- [YOLO / auto-approve mode](/glossary/yolo-auto-approve-mode/): Auto-approve mode, often called YOLO mode, lets an agent run actions without asking each time.

Short answers to 30 common questions are on the [FAQ page](/faq/).

## Sources

- Method: https://aiendpointsecurityranked.com/method/ (read 12 Nov 2026)

Last reviewed 12 Nov 2026. Canonical: https://aiendpointsecurityranked.com/glossary/
