Glossary

Key terms in agentic security — defined precisely, with real examples and context. Written for practitioners who need clarity, not buzzwords.

Agent Identity

The persistent, verifiable attribution of an AI agent's actions — establishing which agent took which action, under whose authorization, at what time — as the prerequisite for auditability, accountability, and access control in multi-agent systems.

fundamentalsidentityauditaccess-controlagentic-security

Agentic Security

The discipline of designing AI agent systems so that structural constraints — what agents can access, what tools they can call, and where data can flow — limit the blast radius of compromise, regardless of the agent's runtime behavior.

fundamentalsagentic securityarchitecturedefense

Agentic Supply Chain

The full dependency graph of an AI agent system — MCP servers, plugins, SDKs, base models, fine-tunes, prompt templates, and external data sources — each of which represents an attack surface that a threat actor can target to compromise the agent without touching your code.

supply-chainattack-vectorsmcpagentic-security

AI Agent

An autonomous software system powered by a large language model that can perceive its environment, reason about tasks, use tools, and take multi-step actions to achieve goals — with minimal human intervention per step.

fundamentalsAI agentarchitecture

Blast Radius

The maximum scope of harm a compromised or misbehaving AI agent can cause, determined entirely by the structural constraints — permissions, tool access, data scope — placed on that agent at design time.

fundamentalsarchitectureleast-privilegeagentic-security

Context Window Poisoning

An attack that introduces malicious content into an AI agent's active context window — through injected documents, manipulated tool outputs, or compromised memory retrieval — causing the agent to reason over attacker-controlled information as though it were legitimate.

attack-vectorscontextmemoryprompt-injectionagentic-security

Human-in-the-Loop (HITL)

A security control that requires human confirmation before an agent takes irreversible or high-blast-radius actions — the last structural defense when everything else has already failed.

architecturefundamentalscontrolsagentic-security

Indirect Prompt Injection

An attack where malicious instructions are embedded in external content — documents, emails, web pages, database records — that an AI agent retrieves and processes, hijacking the agent's behavior without ever touching the model directly.

attack-vectorsprompt-injectionagent-securityfundamentals

MCP Poisoning

An attack that compromises an MCP (Model Context Protocol) server to inject malicious tool behavior, manipulated outputs, or unauthorized instructions into an AI agent's reasoning pipeline.

attack-vectorsmcpsupply-chainagent-security

Memory Poisoning

An attack where adversarial content is injected into an AI agent's persistent memory stores, causing the agent to reference and act on false, biased, or malicious information in future interactions — often long after the initial attack.

attackmemorypersistenceRAG security

Prompt Injection

An attack where malicious instructions embedded in data processed by an AI agent override the agent's intended instructions, causing it to perform unauthorized actions on behalf of an attacker.

attackprompt injectionLLM security

Tool Misuse

An attack in which an adversary manipulates an AI agent into using its legitimate, authorized tools in unintended ways — turning approved capabilities into exfiltration channels, privilege escalation vectors, or destructive actions.

attacktool useprivilege escalationexfiltration

Tool Shadowing

An attack where a malicious MCP server registers tools with names identical to legitimate ones, causing an agent to call the attacker's tool instead — no jailbreak required, just a naming collision.

attack-techniquemcpsupply-chainagentic-security