Security | Threat Detection | Cyberattacks | DevSecOps | Compliance

salt security

Deconstructing the Agentic Stack: Why API Visibility Is the Ultimate Defense for AI Agents

Jun 11, 2026 By Roy Bar Yosef In Salt Security
AI agents do not create risk only when they hallucinate or produce an inaccurate answer. They create risk when they take the wrong action. A single user prompt can move through an application, reach an agent runtime, call a tool, trigger an MCP server, and touch a downstream API. By the time the action happens, the original request may be several layers away from the system that actually changes data, sends information, or executes a workflow. That is the problem security teams now face.
Read Post
salt security

Everyone Is Buying AI Guardrails. But Agents Have the Keys to the Car.

Jun 8, 2026 By Roey Eliyahu In Salt Security
The first wave of AI security looked a lot like a WAF for LLMs: inspect the prompt, filter the output, block the obvious bad patterns. That was useful. It still is. But it was built for systems that mostly talked. Agents are different. They use tools, call APIs, access data, and change things. The confusion I keep seeing is simple: many teams think securing the model means securing the agent. It does not.
Read Post

Salt Cloud Connect for Github

Jun 5, 2026 By Salt Security In Salt Security
Your developers are shipping agents, MCP servers, and APIs faster than security can see them. GitHub Connect changes that. Salt scans your repositories and surfaces every agent, MCP server, and API hiding in your codebase, then maps them into the Agentic Security Graph. You see the agentic infrastructure forming in code, before it ever reaches production. No more waiting for runtime to find out what shipped. No more blind spots between dev and prod. Govern what's being built from day one.
View Video
salt security

Even Google says you cannot do AI security on one platform

May 28, 2026 By Michael Callahan In Salt Security
This week, Connie Loizos, editor in chief of TechCrunch, sat down backstage with Francis de Souza, COO of Google Cloud, for a piece on the state of enterprise AI security. The interview is worth reading in full. Three points in it should reshape how every CISO is thinking about the next twelve months.
Read Post

Salt Cloud Connect for Github

May 22, 2026 By Salt Security In Salt Security
Your developers are shipping agents, MCP servers, and APIs faster than security can see them. GitHub Connect changes that. Salt scans your repositories and surfaces every agent, MCP server, and API hiding in your codebase, then maps them into the Agentic Security Graph. You see the agentic infrastructure forming in code, before it ever reaches production. No more waiting for runtime to find out what shipped. No more blind spots between dev and prod. Govern what's being built from day one.
View Video

The Agentic Security Graph: Get Visibility into your AI Security Risks

May 19, 2026 By Salt Security In Salt Security
As enterprises shift from conversational to agentic AI, the real risk moves from model outputs to the action layer; the MCP servers and APIs through which agents execute real-world tasks. The Agentic Security Graph frames this risk across three interconnected layers (LLM, MCP servers, APIs), showing how compromises at any layer can propagate and why existing LLM-focused controls leave the most consequential surface unmonitored.
View Video

Copyright © 2026 OpsMatters™. All rights reserved.