# AI agent security glossary

URL: https://aiagentsecuritysolutions.com/glossary/
Updated: 2026-11-16

Twenty-eight terms define the vocabulary of AI agent security, from agent runtime, agent registry and non-human identity to kill switch, blast radius, memory poisoning and goal hijacking. Each entry gives a short definition and one sourced example read on 16 Nov 2026.

## 28 terms

- [A2A protocol](/glossary/a2a-protocol/): The A2A protocol, short for Agent2Agent, is an open specification that lets agents built on different frameworks discover each other's capabilities and exchange tasks and messages.
- [Access request workflow](/glossary/access-request-workflow/): An access request workflow is the path by which a user or agent asks for something policy blocks, and an administrator approves or denies it.
- [Agent credential vault](/glossary/agent-credential-vault/): An agent credential vault is a managed store for the keys, tokens and secrets an agent needs, kept outside the agent so it never holds them in plain view.
- [Agent framework](/glossary/agent-framework/): An agent framework is a code library that supplies the building blocks for an agent: model calls, tool definitions, memory and control flow.
- [Agent lifecycle](/glossary/agent-lifecycle/): The agent lifecycle is the sequence from creating an agent through approval, change, monitoring and retirement.
- [Agent observability](/glossary/agent-observability/): Agent observability is the collection of prompts, responses, tool calls and outcomes that show what an agent did and why.
- [Agent orchestration](/glossary/agent-orchestration/): Agent orchestration is the logic that decides which agent or tool acts next, passes state between steps and handles retries.
- [Agent registry](/glossary/agent-registry/): An agent registry is a central list of the agents, tools and skills in use, with an owner and an approval status for each.
- [Agent runtime](/glossary/agent-runtime/): An agent runtime is the software environment in which an AI agent executes its loop of model calls, tool calls and state handling.
- [Agent sprawl](/glossary/agent-sprawl/): Agent sprawl is the spread of AI agents across platforms, SDKs and employee machines without a central record of who owns them or what they can reach.
- [Agent trace](/glossary/agent-trace/): An agent trace is the ordered record of one agent session: the prompts, the tool calls, the results and the downstream actions they caused.
- [AI browser](/glossary/ai-browser/): An AI browser is a web browser with a built-in AI assistant that can read pages, fill forms and take actions for the user.
- [Autonomy level](/glossary/autonomy-level/): An autonomy level states how much an agent may do on its own, from suggesting actions to acting without any approval.
- [Blast radius](/glossary/blast-radius/): Blast radius is the amount of data, systems and other agents that one compromised or misbehaving agent can reach.
- [Goal hijacking](/glossary/goal-hijacking/): Goal hijacking is an attack in which hostile content changes what an agent is trying to do, so it pursues the attacker's aim instead of the assigned task.
- [Guardrail policy](/glossary/guardrail-policy/): A guardrail policy is a written rule that maps a detected condition to an action, such as alert, block, redact or log.
- [Just-in-time access](/glossary/just-in-time-access/): Just-in-time access grants an identity a permission only when a task needs it and removes it when the task ends.
- [Kill switch](/glossary/kill-switch/): A kill switch is a control that stops an agent, cuts its access or isolates it when risk is high.
- [LLM gateway](/glossary/llm-gateway/): An LLM gateway is a proxy that sits between applications or agents and the AI models they call.
- [Memory poisoning](/glossary/memory-poisoning/): Memory poisoning is the planting of false or hostile instructions in the long-term memory an agent keeps between sessions.
- [Model routing](/glossary/model-routing/): Model routing is the practice of sending each request to a model chosen by cost, task or policy.
- [Multi-agent system](/glossary/multi-agent-system/): A multi-agent system is a set of AI agents that divide a task and pass work, context and results to each other.
- [Non-human identity](/glossary/non-human-identity/): A non-human identity is an account, key, token or certificate used by software or a machine instead of a person.
- [OAuth scope](/glossary/oauth-scope/): An OAuth scope is a label in an OAuth request that names the kind of access a token grants, such as read-only access to one resource.
- [Permission boundary](/glossary/permission-boundary/): A permission boundary is a ceiling on the permissions an identity can receive, set apart from the policies that grant them.
- [SaaS agent](/glossary/saas-agent/): A SaaS agent is an AI agent that runs inside a software-as-a-service platform, using that platform's data, tools and identity model.
- [Unbounded consumption](/glossary/unbounded-consumption/): Unbounded consumption is runaway use of model calls, tokens or compute, either by accident or on purpose.
- [Workspace agent](/glossary/workspace-agent/): A workspace agent is an AI assistant or agent embedded in productivity and collaboration software, with delegated access to a user's documents, mail and chats.

## Related pages

- [Guides](/guides/)
- [FAQ](/faq/)
- [The ranking](/ranking/)
- [Layer Coverage Map](/layer-coverage-map/)
- [Agent Control Point Map](/agent-control-point-map/)
