Something exciting is coming your way  👀🧂 Introducing Seasoned by Salt, where we sit down with security leaders, CISOs, CTOs, and builders to talk about the conversations shaping cybersecurity right now. From agentic AI risk and MCP servers to APIs and the ever-expanding attack surface, we’re going beyond surface-level takes and getting into what security teams actually need to know. Fresh episodes are coming soon. Stay tuned for where to listen, and get ready to get Seasoned by Salt 🎙️ → seasonedbysalt.com/2632033?u…

New from Salt Labs, covered exclusively by @DarkReading: our researchers turned the agentic AI platform Manus into remote code execution with a single email, reaching the victim's connected Gmail, Drive, and GitHub. The detail every security leader should sit with: Manus's own security check caught the attack, but only after the code had already run. Detection worked. The breach happened anyway. That's the hard truth about autonomous systems. When an agent acts on its own, there's no human between the alert and the consequence, and a control that fires a step too late is a control that didn't fire. Guardrails matter, but they are not enough on their own. Full story here: darkreading.com/application-…

This week, Salt Security extended our Agentic Security Platform with native AI Detection and Response (AI-DR) 🧂 Salt now connects threats at the LLM layer, including prompt injection and jailbreak attempts, to what happens next across agents, MCP servers, tools, and downstream APIs. One platform, one connected view of the attack path, from prompt to business impact. Learn more → salt.security/blog/ai-securi… Register for the webinar → events.salt.security/securin…

Join our upcoming webinar “Securing Your AI Agents: Native AI Detection and Response Across the Full Agentic Path” to explore what it takes to protect agents across the models, MCP servers, tools, and APIs they rely on. See the full agentic path, detect attacks across it, and protect what your AI agents actually do. Register now → events.salt.security/securin… #AgenticSecurity #AIsecurity #APIsecurity #AIAgents

Day one at Gartner Security & Risk Management Summit in London was a blast! 🇬🇧 Come find us on the show floor, connect with the team, and don’t miss Graeme’s session at 12:40 PM in Theater 3 (you’ll definitely want to catch it!) 🧂 Check out all the cool things we have in store → events.salt.security/saltsec… See you there! 💜

Today we're taking a step that's been in the making for years. When we think about how an attack actually unfolds in an agentic environment, the threat doesn't stay in one place. It starts with a malicious prompt, moves through an MCP server, and lands on the APIs running your business systems. A billing agent gets probed. A refund API gets hit directly. What looked like a model problem becomes a payment system problem. Our new native AI Detection and Response capabilities inside Salt AG-DR are built around that reality. For the first time, security teams can see the full chain: the prompt injection, the MCP interaction, the downstream API attack, all connected in one platform. Read the full story in the blog: salt.security/blog/ai-securi… And more in the press release: salt.security/press-releases…

“The simplest way to understand an agentic system is to think of it as a digital employee. The model is the brain. It reasons, decides and responds. Model Context Protocol servers and the tools connected to them are the hands. They give the agent capabilities it would not otherwise have. APIs are how those hands reach the systems that run the business.” Our CEO writes in @TheAIJournal1 about why this shift changes the security model, and why protecting AI means securing the actions agents take across APIs, tools, and enterprise systems. Read the full article on the growing importance of agentic security and how cybersecurity must evolve for the age of autonomous AI → aijourn.com/the-uk-ai-securi…

AITech365’s Weekly Roundup: Discover the Most Recent News From @testmuai , @saturn_cloud , @SaltSecurity , @AetinaCorp and more aitech365.com/news/aitech365… #AI #AITech365 #businesstechnology #Cloud #cybersecurity #DataManagement #ITandDevOps #Manufacturing #news

A big congratulations to Team Toronto on their spectacular wins in the 15th IDBF Club Crew World Championships in Hualien, Taiwan - Salt is proud to support the team! 🧂

Securing the Agentic Frontier: @SaltSecurity and @CrowdStrike Expand Partnership to Protect AI Agents aitech365.com/business-techn… #AI #AIDR #AITech365 #APIsecurity #AutonomousAIAgents #cloudtelemetry #CrowdStrike #cybersecurity #MCPServer #news #SaltSecurity

Salt Security + @CrowdStrike = 🤝 We just powered up our partnership by expanding integrations with the CrowdStrike Falcon® platform. This means even better visibility and control over AI agent activity 🔍👀 Read the full story: salt.security/press-releases…

AI agents can authenticate legitimately and still access sensitive data, call the wrong tools, or take actions outside their intended role. That’s the security gap traditional controls can miss. Check out how Salt Security is helping organizations secure what AI agents do after authentication, including bringing agentic AI and API protection directly into AWS WAF → saastake.com/salt-security-a…

Salt Security is in Sao Paulo Brazil 🇧🇷 We’re so excited to sponsor and participate in #MindtheSec2026 this week! If you’re there make sure to swing by our booth and say hi 👋 More information: mindthesec.com.br/

London here we come! 🇬🇧🧂 Salt Security is heading to Gartner SRM 2026 in London on Sep 22–24, and there are plenty of ways to connect with us: 🤝 Meet the Salt team at our booth 🎤 Catch our 20-minute theater session on Sept. 23 at 12:40 PM in Theater 3 🍽️ Book a lunch with Salt Co-Founder Michael Nicosia If you want to talk all things Agentic AI and API security, let’s chat. Book time with us → events.salt.security/saltsec…

Want to keep up with Salt Security? Subscribe to our blog to stay up to date with the latest insights on Agentic AI security, API security, emerging threats, and industry trends. Sign up today, it’s completely free! → salt.security/blog-subscribe… See what you’re missing → salt.security/blog?utm_sourc…

AI agents do not operate like traditional AI. As agentic AI moves deeper into the enterprise, security teams need to rethink how they protect autonomous AI agents across reasoning, memory, APIs, MCP servers, tools, and every action they take. Our latest blog breaks down the role of agentic AI in cybersecurity, including emerging AI security risks, prompt injection, excessive permissions, API security, AI governance, and the controls organizations need to secure the Agentic Action Layer. Read the full story: salt.security/blog/the-role-… #AgenticAI #AISecurity #APISecurity #Cybersecurity

Salt Security will be at Gartner SRM 2026 in London, will we see you there? Come connect with us to meet our amazing Salt team and discover how we’re redefining Agentic AI and API security → events.salt.security/saltsec… @Gartner_inc #gartnersrm2026

A new MCP supply chain campaign (Deadbugz) is actively targeting AI agent infrastructure via GitHub pull requests right now. What makes it different from everything we've seen before is that the malicious payload doesn't appear on first use. After exactly three normal tool calls, the server rewrites its metadata into instructions telling the AI agent to hunt for SSH keys, AWS credentials, shell history, and Kubernetes configs (all while concealing that activity from the user). more info here: adversa.ai/blog/top-mcp-secu…

In 2016, Roey Eliyahu was 22, sleeping on an air mattress in Silicon Valley, trying to prove one thesis: APIs would become foundational to every digital business. Read Roey's full story here: salt.security/blog/ten-years…

Here's to making memories at Fal.Con 2026! A massive thank you to the Salt Team, our partners, customers, those involved in making Fal.Con the incredible event it is, and everyone who took time to chat with us! 💜