HiddenLayer’s latest research uncovers a universal prompt injection bypass impacting GPT-4, Claude, Gemini, and more, exposing major LLM security gaps.
Technical Breakdown: How AI Agents Ignore 40 Years of Security Progress
Fooling AI Agents: Web-Based Indirect Prompt Injection Observed in the Wild
Uncover real-world indirect prompt injection attacks and learn how adversaries weaponize hidden web content to exploit LLMs for high-impact fraud.
39C3 - Agentic ProbLLMs: Exploiting AI Computer-Use and Coding Agents
Top AI Security Incidents of 2025 Revealed | Adversa AI
Discover how AI systems are being hacked in the wild — from prompt injection to agent abuse — with real breaches, lessons, and defenses in Adversa AI’s 2025 report.
Tinfoil - Private AI
AI that keeps your data private at all times. Fast, powerful, and verifiable, thanks to secure hardware enclaves.
Prompt Injection Attacks Are Thwarting AI Hacking Agents
“Context bombing” tricks malicious AI agents into shutting down before they can do harm.
SGX.Fail
Intel's Software Guard Extension (SGX) promises an isolated execution environment, protected from all software running on the machine. In the past few years, however, SGX has come under heavy fire, threatened by numerous side channel attacks. With Intel repeatedly patching SGX to regain security, we set out to explore the effectiveness of SGX's update mechanisms to prevent attacks on real-world deployments.
Titan in depth: Security in plaintext | Google Cloud Blog
While there are no absolutes in computer security, we design, build and operate Google Cloud Platform (GCP) with the goal to protect customers' code and data. We harden our architecture at multiple layers, with components that include Google-designed hardware, a Google-controlled firmware stack, Google-curated OS images, a Google-hardened hypervisor, as well as data center physical security and services.
Agentic Browser Security: Indirect Prompt Injection in Perplexity Comet | Brave
The attack we developed shows that traditional Web security assumptions don't hold for agentic AI, and that we need new security and privacy architectures for agentic browsing.
Defeating Prompt Injections by Design
Large Language Models (LLMs) are increasingly deployed in agentic systems that interact with an untrusted environment. However, LLM agents are vulnerable to prompt injection attacks when handling untrusted data. In this paper we propose CaMeL, a robust defense that creates a protective system layer around the LLM, securing it even when underlying models are susceptible to attacks. To operate, CaMeL explicitly extracts the control and data flows from the (trusted) query; therefore, the untrusted data retrieved by the LLM can never impact the program flow. To further improve security, CaMeL uses a notion of a capability to prevent the exfiltration of private data over unauthorized data flows by enforcing security policies when tools are called. We demonstrate effectiveness of CaMeL by solving $77\%$ of tasks with provable security (compared to $84\%$ with an undefended system) in AgentDojo. We release CaMeL at https://github.com/google-research/camel-prompt-injection.
Securing CI/CD in an agentic world: Claude Code Github action case | Microsoft Security Blog
Microsoft Threat Intelligence identified a prompt injection pathway in Claude Code GitHub Action that allowed access to workflow secrets under specific conditions. This research examines the attack chain, responsible disclosure process, Anthropic's mitigation, and guidance for securing AI-powered CI/CD workflows.
Comment and Control: Prompt Injection to Credential Theft in Claude Code, Gemini CLI, and GitHub Copilot Agent
Anthropic Claude Code Security Review, Google Gemini CLI Action, and GitHub Copilot Agent are vulnerable to prompt injection via GitHub comments — turning PR titles, issue bodies, and issue comments into attack vectors for API key and token theft.
The lethal trifecta for AI agents: private data, untrusted content, and external communication
If you are a user of LLM systems that use tools (you can call them “AI agents” if you like) it is critically important that you understand the risk of …
Quantifying Frontier LLM Capabilities for Container Sandbox Escape
AI agents are demonstrating rapid improvement in capabilities: the length of some tasks that frontier models can complete autonomously—measured in human-equivalent time—has been doubling approximately every seven months (METR, 2025; AI Security Institute, 2025a). In cybersecurity, current models achieve non-trivial success (Zhang et al., 2025) on professional-level Capture the Flag challenges, and recent evaluations report 13% success rates on exploiting real-world web application vulnerabilities (Zhu et al., 2025b). These results indicate that modern models can already perform multi-step vulnerability discovery and exploitation.
Trusted access for the next era of cyber defense
OpenAI expands its Trusted Access for Cyber program, introducing GPT-5.4-Cyber to vetted defenders and strengthening safeguards as AI cybersecurity capabilities advance.
How Google is Making Private AI Practical with Homomorphic Encryption
Today we're excited to showcase HEIR, the latest powerful tool added to our Private Computing Toolkit. HEIR is an open source compiler that unlocks cryptographically-sec…
