I shared a post on the OpenAI forum about using Pomerium to secure remote MCP servers with Zero Trust. It’s all open source. We show how to expose MCP servers (like GitHub or Notion) to LLM clients without leaking tokens or re-implementing OAuth.

Happy to chat more over a coffee chat or podcast!

https://community.openai.com/t/zero-trust-architecture-for-mcp-servers-using-pomerium/1288157 #ztna #security #mcp #agenticai

"As AI agents powered by Large Language Models (LLMs) become increasingly versatile and capable of addressing a broad spectrum of tasks, ensuring their security has become a critical challenge. Among the most pressing threats are prompt injection attacks, which exploit the agent’s resilience on natural language inputs — an especially dangerous threat when agents are granted tool access or handle sensitive information. In this work, we propose a set of principled design patterns for building AI agents with provable resistance to prompt injection. We systematically analyze these patterns, discuss their trade-offs in terms of utility and security, and illustrate their real-world applicability through a series of case studies."

https://arxiv.org/html/2506.08837v2

#AI #GenerativeAI #LLMs #PromptInjection #AIAgents #AgenticAI #CyberSecurity

Agentic AI marks a turning point.
It’s not just smart — it acts independently.
Are we evolving, or being engineered out?

#PostHumanShift #AIandSociety #AgenticAI #DigitalDisplacement #TheInternetIsCrack #FediTech

🔥 AI used to talk — now it acts.

Ever wonder why LLMs couldn't "do stuff" before?

Here’s the DevOps-level hack powering real-world automation: agents.

🤖💡 Cloud-native meets AI ops 👇

Watch now: https://youtube.com/shorts/zlbcp2cjASY

#AI #DevOps #LLM #CloudNative #AgenticAI #MLOps

"AI agents have already demonstrated that they may misinterpret goals and cause some modest amount of harm. When the Washington Post tech columnist Geoffrey Fowler asked Operator, OpenAI’s ­computer-using agent, to find the cheapest eggs available for delivery, he expected the agent to browse the internet and come back with some recommendations. Instead, Fowler received a notification about a $31 charge from Instacart, and shortly after, a shopping bag containing a single carton of eggs appeared on his doorstep. The eggs were far from the cheapest available, especially with the priority delivery fee that Operator added. Worse, Fowler never consented to the purchase, even though OpenAI had designed the agent to check in with its user before taking any irreversible actions.

That’s no catastrophe. But there’s some evidence that LLM-based agents could defy human expectations in dangerous ways. In the past few months, researchers have demonstrated that LLMs will cheat at chess, pretend to adopt new behavioral rules to avoid being retrained, and even attempt to copy themselves to different servers if they are given access to messages that say they will soon be replaced. Of course, chatbot LLMs can’t copy themselves to new servers. But someday an agent might be able to.

Bengio is so concerned about this class of risk that he has reoriented his entire research program toward building computational “guardrails” to ensure that LLM agents behave safely."

https://www.technologyreview.com/2025/06/12/1118189/ai-agents-manus-control-autonomy-operator-openai/

#AI #GenerativeAI #AIAgents #AgenticAI #CyberSecurity #LLMs #Chatbots

𝑴𝑨𝑪𝑯 (https://lnkd.in/gpbBbEJs) gave us the blueprint for composable digital experiences.

But as #AI evolves, so must the architecture. I’m proposing a new paradigm: 𝑴𝑨𝑷𝑺, built for the era of #AgenticAI:
https://www.linkedin.com/posts/shishs_how-a-tech-start-up-tackles-legacy-systems-activity-7339048155579150338-wN-J?utm_source=share&utm_medium=member_desktop&rcm=ACoAAAA-mBkBD-GU_2lDGUH3NzxTnUUduSl5dLM

The only #agenticAI I want is the #AI #agent that files a lawsuit on my behalf against the companies operating the AI.

Bonus if it also barfs out the evidence against them.