Resource hub

Explore our articles to learn more about what we do and how we can help.

Beyond the lethal trifecta

Research

Beyond the lethal trifecta

The lethal trifecta has become the default model for reasoning about AI agent risk, but it only captures the confidentiality corner. As agents gain tools, integrity and availability risks demand a fuller model built on data flow.

Yusuf Hussein ·

Agent security is a workflow problem

Field notes

The Meta AI security incident shows the risk of unauthorized agentic workflows

Attackers reportedly used Meta's AI support assistant to take over high-value Instagram accounts by combining legitimate capabilities into an unauthorized workflow. The broader lesson is that tool-calling AI agents introduce security risks at the workflow level.

Thomas Vissers ·

Banking AI assistant security risk

Case study

How we helped a leading European bank secure their financial AI assistant

Blue41 tested how a European banking AI assistant handled untrusted transaction data. The case shows why financial institutions need runtime visibility and layered controls when deploying AI assistants in banking.

Thomas Vissers & Tim Van hamme ·

Field notes

Lessons from the Blue41 x OWASP workshop on breaking AI guardrails

Tim Van hamme ·

System level defenses and visibility will protect AI agents

Research

Inside the AI security conclave

At last week's invite-only Dagstuhl Seminar on LLM Security, Blue41 joined leading researchers from academia and industry in reaching a clear consensus: AI security must evolve beyond input-output filtering to systems-level defense.

Tim Van hamme ·

AI guardrails get broken

Research

Why AI security must move beyond guardrails

Researchers from OpenAI, Anthropic, Google DeepMind, and ETH Zürich published a joint study with a sobering conclusion: the guardrails protecting today’s AI applications can be bypassed across the board.

Thomas Vissers ·

Playground

Research

Jailbreaking: The Researcher's Playground

Jailbreaking: Not just a researcher's game. Discover why today's AI safety measures might be more fragile than you think.

Tim Van hamme ·

Prompt Injection 101

Explainer

Unmasking Prompt Injection Attacks

This article explains what (indirect) prompt injection attacks are, how they differ from jailbreaks, and offer key strategies to secure LLM-powered systems.

Tim Van hamme ·

Real-world attacks

Case study

Real-world attacks on LLM applications

Attacks like prompt injections, indirect prompt injections, and the inherent issue of hallucinations are not just theoretical threats—they are being actively exploited and cause damage to businesses.

Thomas Vissers ·

Hallucinations

Explainer

Hallucinations: LLMs' major reliability problem

Despite the powerful capabilities of LLMs, enterprises face challenges when moving from prototypes to production-grade AI deployments. A key concern when exposing LLM-based systems to the real word is reliability, most notably exemplified by so-called hallucinations.

Thomas Vissers ·

Cyber Security Coalition

Field notes

LLMs: The Next Frontier in Cybersecurity?

This post delves into the intricacies of LLMs, exploring how they work and the vulnerabilities they present, especially when used in applications such as AI assistants.

Jo De Brabandere ·