PENETRATION TESTING · AI SECURITY · SWITZERLAND
For banks, insurers and regulated teams: web apps, APIs and AI agent tool chains tested by Robert Ressl (CISSP, OSEP, OSWE, OSCP).
From CHF 3’900 per package · CHF 2’200 per day
SECURITY READINESS CHECKStart the checkBased in Wollerau, SwitzerlandWorldwide remote & on-siteBackground checks & NDA before scoping
FROM THE FIELD
The report named the exploit path, the precondition and the exact fix. Our developers could reproduce each finding without asking a single follow-up question.
Scoping took one call and produced a target list we both signed. Nothing in the engagement drifted from it, and the retest told us precisely what was closed and what was not.
Published with the client’s approval. Names and employers are withheld at their request; full references are released under NDA before scoping.
01 / Services
01RED TEAM & ADVERSARY SIMULATION
Red teaming and adversary simulations that test people, processes, and technology against realistic attack paths.
02MANUAL PENETRATION TESTING
Authorized, clearly scoped penetration testing that turns exploitable weaknesses into prioritized fixes.
03MODEL, AGENT & TOOL CHAIN
Attack the model, agent, and tool chain before someone else does. Find practical attack paths and help harden the controls around them.
04LOCAL INFERENCE & RAG
Build local inference, RAG, and agent systems for high-security environments—from model training and tuning to production operations.
05STRATEGY & GOVERNANCE
Strategy, architecture, governance, and resilience for regulated and high-security environments.
06TWO-DAY TEAM TRAINING
Two days of practical secure design, coding, review, and testing for engineering teams.
02 / PACKAGES
Fixed-scope starting points for security, regulated AI adoption, and measurable automation. Choose a package when your scope fits one system or one agent; choose the day rate when it does not. Both are confirmed in writing before work starts.
For organizations of different sizes and industries. Robert’s public CV documents Tier-1 banks, insurers and automotive clients, FINMA, DORA and TLPT environments: 100+ on-site engagements across 11 countries. References under NDA on request.
START WITH CLARITY
CHF 3’900
2 working days
Prioritize security risks and AI opportunities before committing to a larger assessment or build.
AUTHORIZED TESTING
CHF 9’800
5 working days
Find exploitable weaknesses in one web application and turn them into prioritized, reproducible remediation.
AGENT & TOOL-CHAIN DEFENSE
CHF 14’800
8 working days
Attack one agent and its tool chain, then help harden the controls that contain real attack paths.
AUTOMATION WITH CONTROL
CHF 24’800
12 working days
Turn one costly workflow into a secure, evaluated agent pilot—with controls and measurable operating assumptions, not automation theatre.
Flexible engagements: CHF 2’200 per working day. Longer, clearly scoped remote projects: CHF 2’000–2’100. Short-notice OT, red-team, and high-security engagements: CHF 2’400–2’600, subject to scope. Package prices are fixed-scope equivalents at CHF 1’850–2’100 per working day; the day rate applies when the scope cannot be fixed in advance.
All package prices and day rates exclude applicable VAT and pre-approved travel and third-party costs, unless expressly included in the order form. Fixed-price packages apply within their stated scope. Scope, authorization, and start date are confirmed in writing before work begins. Regulatory mapping is technical, not legal advice. Savings and compliance outcomes are not guaranteed.
03 / Approach
A clear process before, during, and after the technical work. You always know what is in scope, what happens next, and which artifact you receive. Phases and deliverables depend on the selected package and written scope. Assessments recommend and verify client fixes; hands-on remediation or pilot implementation is included only when expressly scoped.
Clarify objectives, systems, data classification, constraints, and the result your team needs. A short confidential scoping call becomes a written target list, success criteria, and fixed or separately agreed scope. Before testing, the system owner then approves targets, roles, timing, evidence handling, and stop conditions.
Your responsibility Name a technical contact, confirm ownership, and provide the agreed accounts, roles, and environment access. No secrets or sensitive exploit details in the first enquiry.
Test manually, research, or build hands-on, limited to the agreed scope with short checkpoints. AI-assisted work is verified by Robert before it becomes evidence. Findings and design decisions are then explained in business and technical terms, each with preconditions, reproducible evidence, impact, root cause, and a prioritized fix—without inflated severity.
Your responsibility Answer technical questions, flag operational constraints early, and bring the people who can assess impact and implement fixes.
Review remediation and control changes together, then repeat the relevant test or evaluation. Results distinguish fixed, partially fixed, and open items, including residual risk. Finish with an operating guide, knowledge transfer, and next-step decisions; ongoing support is a separate, explicit scope.
Your responsibility Apply agreed fixes, provide the updated build or configuration, and confirm owners for the remaining actions.
One direct technical contact throughout. No black box, no junior handoff, and no sensitive details in the initial form.
04 / PROOF
Four verified below; the rest are listed in the View full CV
Public disclosure of a critical WordPress Core vulnerability, grounded in reproducible technical research.
MCP runtime policy and audit controls with mcp-firewall, plus pre-deployment scanning with mcpwn.
Published work on model behavior, quantization, and deployable formats.
05 / About
Robert Ressl
Safematix is founded and led by Robert Ressl, a Swiss security and AI systems engineer. His work spans Linux and cloud platforms, global offensive-security delivery, model engineering, and regulated production. You work directly with the person doing the technical work.
Willing to complete client background checks and to work under NDA before scoping.
Remote worldwide. Travel for on-site engagements by arrangement.
06 / FAQ
In Wollerau, Schwyz, Switzerland, with delivery worldwide.
Both. Remote delivery is available worldwide, with travel for on-site needs by arrangement.
Yes. I am willing to complete client background checks and to work under NDA before scoping.
Yes. Safematix combines offensive security and ethical hacking with model, agent, MCP, and inference expertise.
I reply personally, usually within one business day (Mon–Fri, CET), to arrange a confidential scoping conversation. Do not send secrets or sensitive exploit details through the initial form.
07 / Contact
Tell me what you need to test, secure, or build. No sensitive details at this stage.