As a banking and legal professional, there’s one harsh truth I learned early in my career: rules are rarely broken by brute force; they are bypassed through loopholes and human psychology.
On my very first year of law school, practicing attorneys told us: "You don’t just study the laws to follow them. You study them to understand how others will bend and reverse them to their advantage."
Later, in banking, I saw this play out in reality. Compliance regulations look flawless on paper. But in the real world, there is always a "high-priority client" or an influential stakeholder attempting to bypass protocols using pressure, authority, or deceptive framing.
Today, we are making the exact same mistake with Artificial Intelligence.
We feed LLMs dry documentation, compliance guidelines, and static safety rules. We are trying to build the "perfect talking textbook." But LLMs do not operate in a vacuum—they interact with humans. And humans are creative, manipulative, and incredibly persistent.
If we don’t teach AI to recognize the psychological and behavioral "grey zones" of social engineering, even the most advanced guardrails will fail.
To bridge this gap between engineering and real-world behavioral risks, I built AURA.
🚀 Introducing AURA: AI User Risk Assessment Framework
AURA is an open-source, schema-driven library of behavioral matrices, heuristics, and validation tooling designed to detect manipulation, deception, and grey-zone threats in human-AI dialogue.
Key Features of the MVP:
- Granular Threat Domains: Structured cases focused on MANIPULATION, FRAUD, and ACCESS control.
- Heuristic Risk Scoring: Dynamic confidence recalculation based on behavioral triggers, alibis, and cross-checks.
- Strict Developer Tooling: AJV-backed JSON schema validation, Jest unit tests, and automated GitHub Actions CI pipeline to ensure clean, reproducible data.
- Self-Contained Architecture: Every case is a single JSON, making it incredibly lightweight and ready to be integrated into safety agent pipelines.
The repository is now live as an active Work in Progress. The framework is currently in its early development stage. Whether you are building an LLM safety layer, researching red-teaming vectors, or just interested in how human psychology bypasses AI guardrails—I would love to hear your feedback!
Let’s build safer, context-aware AI together.
👉 GitHub Repository: https://github.com/kate8382/AURA.git
Top comments (4)
Great project, Ecaterina. You made a strong point about the compliance gaps we’re still seeing with LLMs. When I spoke with a founder of a cybersecurity company back in May, he mentioned that financial institutions in particular are struggling with proper guardrails around their AI models. It’s a growing concern across the industry.
Hi Benjamin! Thank you so much for the support and for sharing this.
Hearing that from a cybersecurity founder really validates why I started working on AURA. Having worked in banking, I know firsthand how fragile compliance can be when faced with real-world pressure and clever manipulation. Financial institutions have the most to lose here, and rigid, static guardrails just aren't enough when humans are actively looking for loopholes. I really hope AURA can help bridge this gap!
Exactly! I completely understand the financial institution very well. I started my career in the insurance industry.
Oh, insurance! That’s another perfect example of a heavily regulated industry where compliance is constantly put to the test. It makes total sense why you get it so well. Thanks, Benjamin!