Topic hub
AI security
Definition
AI security — is the practice of securing artificial intelligence systems (models, agent runtimes and the tooling they invoke) against attack, and of investigating incidents in which those systems are the target or the means.
An AI agent has no disk to image. Its reasoning exists in transit, its tool calls leave traces only where someone chose to record them, and the container it ran in is usually gone by the time anyone asks what it did. That is a forensics problem before it is a model-safety problem, and it is where our work sits.
The machine has no disk
Traditional forensics assumes durable state: a disk to image, a memory dump to parse, logs written to a filesystem someone controls. An agent runtime breaks all three assumptions. The prompt, the reasoning trace, the tool invocations and their results may exist only as API traffic, and the compute is frequently ephemeral. Forensic readiness for these systems means deciding what to record before an incident, because afterwards there is nothing to recover.
Where agent incidents come from
The attack surface of an agentic system is not primarily the model. It is the tools the agent can call, the data it ingests that an attacker can influence, the credentials it holds, and the boundary between what it is allowed to propose and what it is allowed to execute. An agent with a shell tool and a prompt-injectable data source is an untrusted code execution path with good manners.
Everything we have published on ai security
1 piece of research, tooling and case-study work.
Common questions
What is AI security?
AI security is the practice of securing artificial intelligence systems (models, agent runtimes, and the tools and data they access) against attack, and of investigating incidents where those systems are the target or the means of an attack. It spans model-level concerns such as prompt injection and system-level concerns such as what an agent is permitted to execute.
What is AI agent forensics?
AI agent forensics is the investigation of what an autonomous AI agent did during an incident: which tools it called, what data it ingested, what it was instructed to do, and what it changed. It is difficult because agent runtimes are typically ephemeral and produce no durable disk artefacts, so the evidence must be deliberately recorded in advance rather than recovered afterwards.
Why is it hard to investigate an AI agent incident?
Because there is usually nothing left to examine. Conventional forensics depends on durable state (a disk to image, a memory dump, filesystem logs) and an agent runtime often has none of these: the reasoning trace exists only as API traffic and the compute is destroyed on completion. Forensic readiness has to be designed in before the incident occurs.
What is prompt injection?
Prompt injection is an attack in which adversary-controlled text reaches a language model as instructions rather than as data, causing the model to act on the attacker’s intent instead of the operator’s. It matters most in agentic systems, where a model that has been redirected can invoke real tools with real credentials.
How we help
Emergency Incident Response
24/7 emergency incident response with an assured four-hour response from first contact: containment, full attack-chain reconstruction, and guided recovery.
T3aaS — Tier 3 as a Service
On-demand senior escalation for your SOC: threat hunting, malware analysis and reverse engineering, and detection engineering, without carrying the headcount.
Related topics
Digital forensics (DFIR)
Digital forensics and incident response (DFIR) is the combined discipline of collecting and analysing digital evidence to establish what happened during a cyber attack, and managing that attack end to end.
Cyber research
Cyber threat research is the systematic investigation of adversary tooling, infrastructure and behaviour — malware analysis, campaign attribution and technique documentation — carried out to make the resulting knowledge usable in defence.
Talk to the team that does the work
The people who publish the research above are the people who take your escalations.