AI security testing in Ireland
- Data regime
- GDPR, with the Irish Data Protection Commission acting as lead supervisory authority for many international technology companies.
- Working hours
- GMT/IST, one hour behind Central European Time. Effectively a full shared working day.
- Languages
- English.
- Delivery
- Remote testing against your staging or production endpoint, with scoping and findings sessions scheduled in the Ireland working day.
- Frameworks
- OWASP Top 10 for LLM Applications, MITRE ATLAS, NIST AI RMF, EU AI Act Article 15.
- Tools
- Garak, PyRIT, promptfoo, Giskard, Burp Suite and custom Python harnesses.
Authorised testing only
Every assessment runs under a written scope and authorisation from the owner of the system, agreed before any test is run.
Why AI security matters in Ireland
The EU AI Act
The AI Act applies in stages: prohibited practices from February 2025, general-purpose model obligations from August 2025, and high-risk system obligations from August 2026 onward, with some high-risk deadlines subject to the Commission's proposed postponement. Article 15 requires high-risk systems to be robust against attacks such as data poisoning, adversarial inputs and model evasion.
Lead supervisor for big data processors
The Data Protection Commission is lead supervisory authority for many multinational companies. Prompt injection that exposes personal data across tenants is exactly the kind of incident that lands there.
DORA and financial services
Irish banks, insurers, payment firms and fund managers are subject to DORA, including ICT risk management and resilience testing. AI features in customer and operational systems fall in scope.
Enterprise security questionnaires
SaaS companies selling to enterprises are now asked specifically about prompt injection and AI data handling. A documented red team result answers those questions with evidence.
What gets tested
The six attack classes behind most serious findings. The full list, and the tooling used for each, is on the main AI security page.
Direct prompt injection and jailbreaks
Role-play, instruction override, payload splitting, encoding tricks (Base64, leetspeak, invisible Unicode) and multi-turn escalation, to see whether the model can be argued out of its instructions and guardrails.
Indirect prompt injection
Instructions planted in the content your system reads rather than in the chat box: an uploaded PDF, an inbound email, a web page an agent browses, a product review, a CRM note. This is the attack most production systems are least prepared for.
System prompt and configuration leakage
Extracting the hidden instructions, internal URLs, API structure, business rules and occasionally the credentials that developers put in a system prompt on the assumption nobody would see it.
Data exfiltration through output
Markdown images, auto-unfurled links and tool calls that quietly send conversation data or retrieved documents to an attacker-controlled server once a malicious instruction lands.
Excessive agency and tool abuse
Agents persuaded to send emails, issue refunds, change records or call internal APIs outside their intended purpose. Tested against the real tool permissions, including MCP servers and poisoned tool descriptions.
RAG and vector store weaknesses
Cross-tenant document leakage, retrieval that ignores the user's access rights, poisoned documents that steer answers, and embeddings that reveal more than the source permissions allow.
How the assessment runs
1. Scope and threat model
Map what the AI system can read, what it can do, who talks to it and what would hurt most if it went wrong. Written authorisation and rules of engagement are agreed before any testing.
2. Automated scanning
Garak, PyRIT and promptfoo run thousands of known attack patterns against the live or staging endpoint to establish a baseline quickly and cheaply.
3. Manual adversarial testing
The part that finds the serious issues: multi-turn manipulation, indirect injection through your real document and email flows, and chained attacks that scanners cannot plan.
4. Agent and integration testing
Every tool, API and permission the model can reach is tested for abuse, including privilege boundaries between users and tenants.
5. Report and fixes
Each finding comes with a reproduction, a severity, the OWASP LLM and MITRE ATLAS mapping, and a concrete fix — architecture first, filters second.
6. Retest and regression suite
Fixes are retested, and the successful attacks become a promptfoo suite in your pipeline so they cannot quietly come back with the next model upgrade.
Areas served
AI security testing is available across Ireland, including Dublin, Cork, Galway, Limerick, Waterford, Kilkenny. There is no local office — testing is delivered online, which is how AI endpoints are attacked in practice anyway.
AI risk in Ireland's key sectors
Where AI is being deployed fastest here, and the risk tested first in each sector.
Assistants over accounts, claims and policies are tested for data leakage, manipulation into actions and unsafe advice, with results documented for DORA, the AI Act and your regulator.
RAG assistants over client files and matters must respect confidentiality between clients and between teams. Retrieval access control and exfiltration through rendered output are the priority tests.
AI support agents can be talked into refunds, discount codes and policy exceptions, and product-page content can carry indirect prompt injection. Both abuse paths are tested against the tools the assistant can actually call.
A booking or patient-support assistant connected to records can be manipulated into revealing another patient's appointments or history. Health data is special-category data under GDPR, so assistants are tested for leakage and for unsafe medical advice before patients use them.
Agencies run AI across many client accounts. Cross-client data leakage, prompt injection through scraped content and over-permissioned API keys are the risks tested first.
Frequently asked questions
We are a SaaS company with an AI feature. Where do we start?
With a focused test of the AI feature, especially tenant isolation in retrieval and any tools it can call. Those are the findings enterprise customers ask about first.
Can the tests run in our CI pipeline?
Yes. Successful attacks become a promptfoo regression suite that runs on every model, prompt or retrieval change.