Research

Research
min read

What’s the ‘Matter’ with Skills?

Leveraging Skill Frontmatter to Attack Claude Code

Research
min read

Updating HiddenLayer’s APE Taxonomy: A New Objective Model for AI Attacks

Research
min read

The Next AI Supply Chain Risk: Malicious Skills in Agentic AI

Skills, the thing no one saw coming, yet will run our lives

Research
min read

Inside the Prompt: How LLMs Learn Roles, Follow Instructions, and Get Exploited

An enterprise team evaluates a third-party model before deploying it into production. During scanning, their security tooling flags a high-risk issue. Engineers now need to determine whether the finding is valid and what action to take before moving forward.

Research
min read

Tokenization Attacks on LLMs: How Adversaries Exploit AI Language Processing

An enterprise team evaluates a third-party model before deploying it into production. During scanning, their security tooling flags a high-risk issue. Engineers now need to determine whether the finding is valid and what action to take before moving forward.

Research
min read

ChromaToast Served Pre-Auth

An enterprise team evaluates a third-party model before deploying it into production. During scanning, their security tooling flags a high-risk issue. Engineers now need to determine whether the finding is valid and what action to take before moving forward.

Research
min read

Tokenizer Tampering

Research
min read

Malware Found in Trending Hugging Face Repository "Open-OSS/privacy-filter"

Research
min read

AI Agents in Production: Security Lessons from Recent Incidents

Research
min read

LiteLLM Supply Chain Attack

Research
min read

Exploring the Security Risks of AI Assistants like OpenClaw

Research
min read

Agentic ShadowLogic

Understand AI Security, Clearly Defined

Explore our glossary to get clear, practical definitions of the terms shaping AI security, governance, and risk management.