AI security testing in Tirana
- Data regime
- Albanian data protection law, aligned with GDPR as part of EU accession. Data can be hosted in-country or in the EU.
- Working hours
- CET. Same working day as the entire EU, with full overlap.
- Languages
- Albanian for staff-facing interfaces, English for technical documentation.
- Delivery
- Remote testing against your staging or production endpoint, with scoping and findings sessions scheduled in the Tirana 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 Tirana
Locally based
Scoping workshops, findings walkthroughs and developer training can be held in person anywhere in Tirana, with the testing itself done remotely.
Outsourcing and software teams
Tirana software firms building AI features for European clients increasingly need to show those features were security tested. A red team report is evidence a client can use.
Banking and telecom assistants
Banks and telecom operators hold exactly the data an attacker wants. Assistants connected to account information are tested for leakage and for manipulation into unauthorised actions.
Albanian-language jailbreaks
Albanian is a lower-resource language for model safety training, so Albanian-language attacks are a core part of every test here.
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 Tirana, including Blloku, Qendra, Ish-Blloku, Komuna e Parisit, Rruga e Kavajës, Laprakë, Kombinat, Yzberisht. There is no local office — testing is delivered online, which is how AI endpoints are attacked in practice anyway.
AI risk in Tirana'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.
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.
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.
Frequently asked questions
Can we meet in person?
Yes. I am based in Tirana, so scoping and the findings walkthrough can happen at your office.
We build AI features for foreign clients. Can you test those?
Yes, with your client's authorisation where the system is theirs. The report is written so it can be handed to the client directly.