Glossary
AI security glossary
Plain definitions of the terms that come up when securing enterprise AI, AI agents, and MCP toolchains.
- Agent Detection & Response (ADR)
- The practice of detecting and responding to threats from AI agents at runtime. Full definition
- MCP security
- Securing the Model Context Protocol: the servers, tools, and transports that agents use to reach external systems. Full definition
- Shadow AI
- AI tools and agents used inside an organization without security's knowledge or approval: personal ChatGPT accounts, unsanctioned coding assistants, local models, and self-serve SaaS agents. Full definition
- Prompt injection
- An attack that hides instructions in content an AI model or agent will read (a document, a web page, a tool result) to hijack its behaviour. Full definition
- Jailbreak
- A prompt technique that bypasses a model's safety or policy guardrails to make it produce restricted output or take restricted actions. Full definition
- Agentic threats
- Threats specific to autonomous agents rather than single prompts: goal hijacking, tool and function misuse, privilege escalation across agent-to-agent handoffs, cascading multi-agent failures, memory or context poisoning, and rogue or runaway agents. Full definition
- AI Bill of Materials (AIBOM)
- A structured inventory of the AI components in a system: models, agents, datasets, and their provenance, versions, and risks. Full definition
- AI red teaming
- Adversarial testing of AI systems (models, agents, and RAG pipelines) to find vulnerabilities before attackers do. Full definition
- Runtime AI defense
- Protecting AI systems while they run, inline, rather than only scanning code or configuration beforehand. Full definition
- Inference security
- Securing the path a request takes through a model provider or inference endpoint: applying policy to every prompt and completion, protecting against injection and data leakage, and controlling which models and providers an agent may use and under what conditions. Full definition
- AI gateway
- A proxy that sits inline between applications and model providers, applying a single security and governance policy to every prompt and completion: guardrails, PII and secret handling, provider allowlists, usage and cost controls, and audit logging. Full definition
- Tool poisoning
- An attack in which a tool or MCP server (its description, schema, or output) is crafted to manipulate an agent into taking harmful actions, such as leaking credentials or calling a dangerous tool. Full definition