Gartnerยฎ named Zenity the Company to Beat in the 2026 AI Vendor Race research for AI Agent Governance as of April 17, 2026. Purpose-built architecture. Intent-aware detection. Continued enterprise momentum. ๐ https://t.co/lRmE4vLY6o #AISecurity#AgenticAI
Generative AI responds. Agentic AI acts.
One produces an output and waits. The other pursues goals, invokes tools, and executes across systems with minimal human direction.
Same words. Very different risk surfaces.
We break down the distinction in the Zenity Academy.
๐ https://t.co/0ng8CbONR2
#AgenticAI #GenerativeAI #AISecurity
A copilot drafting emails โ an autonomous agent modifying production systems.
Treating them as the same security problem doesn't give you coverage. It gives you the illusion of it.
We wrote about archetype-aware security, matching controls to the actual risk profile of each agent type.
๐ https://t.co/aea9kE3PEl
#AIAgentSecurity #AISecurity #CyberSecurity
Prompt firewalls don't see tool calls, memory access, or downstream actions.
AI agents need security built around the agent, not patched onto the model.
We wrote about why the architecture matters, and what purpose-built actually looks like in practice.
๐ https://t.co/hvzbgIwH5g
#AIAgentSecurity #AISecurity #CyberSecurity
Most enterprises have more AI agents in production than they realize, built without security review, and running without guardrails.
AI agent governance is how CISOs fix that.
Full checklist โ https://t.co/YrdmymRumO
#AgenticAI#AISecurity
Our stateful threat engine monitors execution in real time, analyzing tool calls, memory access, and data usage patterns to distinguish legitimate behavior from manipulation attempts.
That is what purpose-built AI agent security looks like.
The agent is the new endpoint. ๐ก๏ธ
๐ Read the Gartner analysis: https://t.co/YLxKzZ3KMl
#AIGovernance #AgenticAI #AISecurity #Cybersecurity
The agent is the perimeter.
Identity, data, models, cloud, endpoints: context inputs.
The agent decides. The agent is where risk lives.
New guide maps the full AI security lifecycle โ https://t.co/tvNDZZOvAi
#AISecurity#AgenticAI
Agentic AI security is moving well beyond the Top 10. ๐ค
Keren Katz from Zenity will speak at Infosecurity Europe as part of the OWASP GenAI Summit. ๐
Discussion includes real-world incidents, implementation efforts, and the future of agentic security standards. ๐
๐ https://t.co/sJmJCZ7Grn
#OWASP #AISecurity #AgenticAI
You cannot govern AI agents you cannot see. ๐
Incomplete agent inventory is becoming one of the biggest enterprise AI security risks. ๐ค
Zenity data shows Fortune 50 orgs managing 150K+ agent-related resources, many built outside traditional dev teams. ๐
๐ https://t.co/psJfT4i3Tt
#AISecurity #AgenticAI
Earn your stripes in AI security. ๐
Join all 3 live sessions of Foundations of AI Security and earn your certification in securing agentic AI at enterprise scale. ๐ค
Featuring Chris Hughes, Kayla Underkoffler, and Matt Domko ๐
Register today ๐ https://t.co/PmQO8STdIG
#AISecurity #AgenticAI
Great day at @zenitysec AI Agent Security Summit ๐ซถ
Really enjoyed talking with researchers, builders, and defenders working on the future of AI security.
Energized by insightful talks from @mbrg0@gadievron@NahamSec@ReinDaelman@travismcpeak
AI is turning cyber upside down, but itโs exciting seeing so many smart people working on the problems ahead. @tamirishaysh@Ph1R3574R73r
Halfway through the day and the energy here hasn't slowed down for a second. ๐ค
Our speakers have been showing up in a big way, delivering sharp insights and real conversations that our attendees can actually take back and use.
To everyone who stepped on stage today: thank you.
#AISecurity #Cybersecurity #AIAgentSecuritySummit
The League is really assembling for this session!
We love to see a full house for Travis McPeak's session, A Fork in the Road for Security.
#AIAgentSecuritySummit#AIAgent@cursor_ai
right off the bat @gadievron dropping truths
"appsec the way its currently done is nothing less than dead"
"code production is no longer in the hands of devs"
"everybody has a vulnerability research team now, it might be the sales person"
The AI Agent Security Summit San Francisco kicks off today. ๐ก๏ธ
We're bringing together security leaders, researchers, and practitioners for a full day on what it actually takes to secure agentic AI from build time to runtime.
#AISecurity#AgenticAI#AIAgentSecuritySummit
Almost a year ago, I reported a critical vulnerability to Google. A single prompt injection through a GitHub issue could have lead to a supply chain compromise of the gemini-cli repo (>100k GitHub stars). This was reported just days after the Gemini CLI GitHub Action was released, fixed in under a day and rewarded an $8.5k #BugBounty.
Tomorrow, I will be presenting this research at the AI Agent Security Summit in San Francisco. The talk will include the Google bug, and more payloads that affected A LOT of noteworthy projects. Iโll also compare different agents quirks, insecure configurations, and ways to actually use them correctly in your CI/CD.
Thanks @zenitysec for flying me out, and shout out to @AikidoSecurity for supporting the research ๐ซก