Patient zero
Also written AI incident
The first point at which malicious content entered an AI system in an incident — the poisoned web page, file, tool description or message an agent read before acting — or the first agent or machine it reached. Finding it tells responders what else may have read the same content, where it may have spread through memory or delegation, and what has to be cleaned up.
Related terms
-
Context tree
Defence & response
In AI incident forensics, a reconstruction of everything that entered a model's context during a session and where each piece came from — prompts, files…
-
Memory / cross-agent propagation
Agents & architecture
A payload that is written in one session and fires in a later one, or in a different agent.
-
Indirect prompt injection
Attack concepts
The instructions are planted in content the agent reads rather than text the user types — a web page, a GitHub issue, a code comment, a dependency's…
Defence & response
The vocabulary of running controls for agents: knowing what AI is present, cutting what it may do down to what it uses, catching misuse, and reconstructing an incident afterwards. Where MoorAI implements a term, a separate line under the definition says how; the definition itself stays vendor-neutral. To check one agent's configuration against these ideas, use the free permission right-sizer.