AI security testing in Amsterdam
- Data regime
- GDPR, implemented nationally as the AVG. EU data residency is straightforward and generally expected.
- Working hours
- CET. Identical working day.
- Languages
- English is standard for technical and business work; Dutch for customer-facing content.
- Delivery
- Remote testing against your staging or production endpoint, with scoping and findings sessions scheduled in the Amsterdam 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 Amsterdam
Payments and fintech
Fintech and payment firms fall under DORA and close supervision. AI assistants with account access are tested for leakage and for manipulation into actions.
Marketplaces and travel
AI support on marketplaces and booking platforms can be pushed into refunds, vouchers or policy exceptions. Those abuse paths are tested explicitly.
Dutch algorithm supervision
The Dutch data protection authority coordinates AI and algorithm oversight, so documented testing carries weight here.
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.
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 Amsterdam, including Zuidas, Amsterdam-Zuid, Amsterdam-Noord, De Pijp, Sloterdijk, Amstelveen, Science Park. There is no local office — testing is delivered online, which is how AI endpoints are attacked in practice anyway.
AI risk in Amsterdam'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.
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.
Booking and concierge bots are public and connected to reservations. They are tested for price manipulation, leakage of other guests' details and unauthorised booking changes.
Assistants over shipment, customer and pricing data must not leak one customer's data to another or be steered into changing records. Documents and emails the system reads are tested as injection vectors.
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
Can you test an AI support agent that issues refunds?
Yes, and it should be tested. Refund and voucher abuse through manipulation is one of the most direct financial risks of AI support.
Is the work in English?
Yes, with Dutch-language attacks included for Dutch-facing systems.