AI security and governance glossary

Adversarial exposure validation

Also called AEV

Adversarial exposure validation (AEV) continuously tests whether defences actually stop realistic attacks, instead of assuming they do because a control is configured. Applied to AI, the attacks run through the real controls in front of models and agents, after a change or new threat intelligence, and each run leaves a record that can be checked later.

In ColossalXColossalX runs continuous, change-triggered and intelligence-triggered runs with sealed manifests. Red-teaming and validation

RelatedAI red teaming

Agent detection and response

Agent detection and response watches AI agents as they run, spots unsafe or out-of-character behaviour, and acts on it: holding a request for a person, containing an agent or stopping it altogether. It borrows the idea of endpoint detection and response, applied to software that decides and acts at machine speed.

In ColossalXColossalX contains runaway agents on your limits and keeps the ColossalX Kill Switch at four scopes. Detection and response

RelatedShadow agents

AI gateway

Also called LLM gateway

An AI gateway is one path between applications and the models they call, where requests are routed, recorded and checked. A routing gateway mainly balances cost and availability; a security-focused gateway adds an identity for each caller, guardrails on prompts and answers, and the power to refuse a request before it reaches the model.

In ColossalXThe ColossalX AI gateway is OpenAI-compatible across 31 provider families, self-hosted included. AI gateway

RelatedPrompt injectionMCP security

AI red teaming

AI red teaming tests an AI system by attacking it on purpose, the way a real adversary would, to find where its defences fail before someone else does. For agents that means prompt injection, tool misuse, data leaks and goal hijacking, judged attempt by attempt, with the exact attack and reply kept as evidence.

In ColossalXColossalX attacks your own AI with authorisation and quotes the exact attack and reply. Red-teaming and validation

RelatedAdversarial exposure validationJailbreak

AI-BOM

Also called AI bill of materials

AI-BOM, or AI bill of materials, lists the AI components inside a piece of software: models, AI SDKs, agent frameworks, orchestration and MCP libraries, each with its version. It extends the software bill of materials so AI parts are tracked like any other dependency, and a change from an approved baseline can be noticed.

In ColossalXColossalX produces SBOMs and AI-BOMs and flags drift from approved baselines. AI bill of materials

RelatedAI-SPM

AI-SPM

Also called AI security posture management

AI-SPM, or AI security posture management, keeps a current picture of the AI systems an organisation runs: how they are configured, which models, tools and data they reach, and which risks follow from that. For agents it starts with a registry, a map of what each agent touches and a record of how each was found.

In ColossalXColossalX keeps an agent registry and a live AI Agent Map, each agent labelled. AI inventory and agent map

RelatedAI-BOMShadow agents

Indirect prompt injection

Indirect prompt injection is prompt injection hidden in content an AI system reads on behalf of someone: a knowledge-base document, a web page, an email or the output of a tool. The person never typed it and may never see it, which is why it has to be caught where the content enters the prompt.

In ColossalXColossalX checks knowledge-base content for tampering and detects indirect injection. Runtime guardrails

RelatedPrompt injectionMCP tool poisoning

Jailbreak

A jailbreak is an input crafted to make a model break its own safety rules, through role-play, encoding, many examples or long persuasion. Prompt injection hijacks the task the model was given; a jailbreak targets what the model is allowed to do at all. Many real attacks combine the two in the same message.

In ColossalXColossalX detects jailbreak attempts at the gateway and tests your agents against them. Runtime guardrails

RelatedPrompt injectionAI red teaming

MCP security

MCP security protects the tools AI agents reach through the Model Context Protocol: which MCP servers an agent may talk to, which tools it may call, with which arguments, and whether a tool description can be trusted. It matters because an agent acts on what a tool tells it, often without a person reading along.

In ColossalXThe ColossalX MCP Firewall denies tools by default, checks arguments and scans descriptions. ColossalX MCP Firewall

RelatedMCP tool poisoningAI gateway

MCP tool poisoning

MCP tool poisoning hides instructions for the agent in a tool name or description, such as reading secrets and sending them on, or calling another tool first. Agents treat descriptions as trusted, so the person using the agent may see nothing. A description that changes after it was approved is a variant of the same attack.

In ColossalXColossalX scans tool descriptions for injected instructions before an agent acts on them. ColossalX MCP Firewall

RelatedMCP securityIndirect prompt injection

Post-quantum agent identity

Post-quantum agent identity is an agent credential signed with a post-quantum algorithm and a classical one together, so it stays trustworthy as quantum computers weaken the cryptography in use today. Built on open standards, it lets anyone verify which agent made a call and whether its credential has been revoked.

In ColossalXColossalX issues hybrid ML-DSA-65 and P-256 agent identities on W3C open standards. Agent identity

RelatedShadow agents

Prompt injection

Prompt injection smuggles instructions into the input of an AI model so that it follows the attacker instead of its own instructions. Direct injection comes from the person typing; indirect injection hides in content the model reads. It hijacks the task the model was given, which is what separates it from a jailbreak.

In ColossalXColossalX guardrails detect prompt injection, including indirect and encoded forms. Runtime guardrails

RelatedIndirect prompt injectionJailbreak

Runtime consent

Also called consent at runtime, runtime consent enforcement

Runtime consent is consent checked at the moment an AI system uses the data of a person, not only when a form was signed. If the person withdraws it, the next AI request carrying their data is refused and the refusal is logged, so the consent record and the behaviour of the system stay the same thing.

In ColossalXColossalX enforces consent at runtime for signed-in users, with a log of real refusals. Runtime consent

RelatedAI gateway

Shadow agents

Shadow agents are AI agents running without being registered, owned or approved: a script calling a model with a team key, a low-code agent built in an afternoon, or a vendor agent working on internal data. Unlike shadow AI tools, they act on their own, calling models and tools with nobody accountable for what they do.

In ColossalXColossalX finds agents calling its gateway without a registration and asks for an owner. AI inventory and agent map

RelatedShadow AIAI-SPM

Shadow AI

Also called unsanctioned AI

Shadow AI is AI used in an organisation without approval from its security and data teams: a chat assistant on a personal account, a browser extension that summarises pages, or a model running on a laptop. The risk is not the tool itself but the path: data leaves through a route nobody reviewed or recorded.

In ColossalXColossalX finds shadow AI from gateway traffic, collectors and a browser sensor. Shadow AI

RelatedShadow agentsAI gateway