@OpenHandsDev: AI agents are a new attack surface. Join @OpenHandsDev and @GraySwanAI for a sharp discussion on prompt injection, agen…
Summary
OpenHands and Gray Swan are hosting an event to discuss AI agent security risks, including prompt injection and agent-specific threats, and how to build secure agents.
View Cached Full Text
Cached at: 07/11/26, 09:36 PM
AI agents are a new attack surface. Join @OpenHandsDev and @GraySwanAI for a sharp discussion on prompt injection, agent-specific threats, and what it takes to build agents that hold up under real attack.
Reserve your spot 👉 https://t.co/g3YcxoxVH1
How AI is Transforming Cybersecurity · Zoom · Luma
Source: https://luma.com/openhands-0yga?utm_content=382277527&utm_medium=social&utm_source=twitter&hss_channel=tw-1793978852919885824 AI agents are already writing code, managing infrastructure, and making decisions with real access to real systems. That’s the upside. It’s also a new attack surface.
Agents introduce risks traditional security teams haven’t had to think about: prompt injection turns an agent’s own instructions into a social engineering target, and an adversary with agentic tooling can move faster and dig deeper than a human ever could. At the same time, agents create real opportunities: automated code audits, faster vulnerability remediation, and monitoring that catches what humans miss.
OpenHands and Gray Swan are teaming up to walk through both sides: how agents get exploited, and how to build ones that hold up under real attack.
What we’ll cover
- How AI agents actually work (the model, the prompt, and the tools you give it)
- The cybersecurity risks unique to agents: attack surface, prompt injection, and AI-aided attacks
- How to secure agents, and how to use agents to secure everything else
- Live discussion and Q&A
Speakers
Graham Neubig, Chief Scientist at OpenHands
Matt Fredrikson, CEO/Co-founderat Gray Swan
Who should attend
Security engineers, platform and infrastructure teams, and engineering leaders evaluating how to roll out AI agents without opening up new risks.
About OpenHands
OpenHands is the foundation for secure, transparent, model-agnostic coding agents, empowering every software team to build faster with full control.
About Gray Swan
Gray Swan provides enterprise-grade security solutions for LLMs, developed by the pioneers of AI vulnerability research.
Similar Articles
How are you all handling prompt injection for agents that read external content?
A discussion about handling prompt injection attacks in AI agents that read external content like emails and webpages, exploring production-level defenses and the subtle threats beyond obvious patterns.
For tool-using agents, where do you draw the security boundary?
A discussion on the security risks of AI agents using tools, focusing on prompt injection as a practical threat where untrusted text can alter agent behavior, and the need for repeatable testing before granting permissions.
Insights on Indirect Prompt Injection (12 minute read)
Zico Kolter and Matt Fredrikson, leaders at Gray Swan and experts in AI security, discuss the state of AI red-teaming and indirect prompt injection, a critical vulnerability for AI agents. They explain why AI security requires a different mindset, how automated red-teaming can beat humans, and introduce tools like Shade for adversarial testing.
Are AI agents creating a new runtime supply-chain attack surface?
Discusses AI agent security as a runtime supply-chain problem beyond prompt injection, highlighting risks from untrusted data, tools, and feedback loops, and questions how developers enforce boundaries.
Designing AI agents to resist prompt injection
OpenAI publishes guidance on designing AI agents resistant to prompt injection attacks, arguing that modern attacks increasingly use social engineering tactics rather than simple string injections, and advocating for system-level defenses that constrain impact rather than relying solely on input filtering.