Security | Threat Detection | Cyberattacks | DevSecOps | Compliance

In Part 1 of this blog series, we explored the architecture, capabilities, and risks of the Model Context Protocol (MCP). In this post, we will focus on two attack vectors in the MCP ecosystem: prompt injection via tool definitions and cross-server tool shadowing. Both exploit how LLMs trust and internalize tool metadata and responses, allowing attackers to embed hidden instructions or persistently influence future tool calls without direct user prompts.

The Cloud Security Alliance, a respected non-profit founded in 2008 to pursue cloud security assurance, has now unveiled its Artificial Intelligence Controls Matrix (AICM), a quiet revolution for trustworthy AI. It has come at a time when generative AI and large language models are moving quickly into every sector. These systems can transform business, but they can also fail, or be made to fail. Because of this, trust becomes the measure of success.

What’s the fastest way to lose trust? Expose private data. With AI moving from pilots to core workflows in support, finance, HR, and healthcare, one careless prompt or leaky integration can turn into headlines, fines, and weeks of incident response. The most useful way to understand the risks is to study AI privacy issues examples from the real world.

You got compliant—congrats! That’s a big milestone. It tells customers, investors, and the world that you take security seriously. But compliance doesn’t stop at your first audit. As your company grows, so do the requirements. You’ll have to manage new frameworks, more policies, faster timelines, more scrutiny, and more complexity. ‍ Modern GRC teams need to do more with less.

We’ve all seen it: a cutting-edge, multimodal LLM, capable of understanding complex documents, stumbles on a seemingly simple task. In our case, the model confidently reported a contract’s signing date as "March 30". The only problem? The document clearly stated "March 9th". It wasn't just a minor error; it was a baffling one that sent us down a rabbit hole of debugging.

When we started Wallarm, we focused on the APIs that power modern apps. We built an API-first platform, used AI from day one, and secured early patents in behavior-based detection and automated policy creation. The result: real-time, inline blocking with automatic API discovery that protects production, not just dashboards. Today’s investment isn’t only fuel for innovation—it’s proof of enterprise recognition.

Throughout the past few years, APIs have become the backbone of digital infrastructure. They enable software-to-software communication, improve integration and interoperability, support modular architecture, and more. But as API use has exploded, so has API traffic volume and complexity, making them increasingly difficult to secure. And the rise of AI agents and automation have complicated matters further. The result? APIs have become a favourite attack vector for cybercriminals.