Cyata | The Control Plane for Agentic Identity

This content is password-protected. To view it, please enter the password below. Password: The post Protected: Cyata Research: From SQLi to RCE - Exploiting LangGraph's Checkpointer appeared first on Cyata The Control Plane for Agentic Identity.

: Prompt injection for the win

How We Found Code Execution in Anthropic's Official Git MCP Server TL;DR What happened: Cyata discovered three security vulnerabilities in mcp-server-git, the official Git MCP server maintained by Anthropic. These flaws can be exploited through prompt inj

Cyata Research: LangGrinch Vulnerability in LangChain Yesterday, LangChain published a critical advisory for a vulnerability I reported in langchain-core: CVE-2025-68664 / GHSA-c67j-w6g6-q2cm. Earlier this year, my research focused on breaking secret mana

As originally published at SiliconANGLE, a new report out today from artificial intelligence security startup Cyata Security Ltd. details a critical remote code execution vulnerability in Cursor Inc.'s integrated development environment that exposed risks

Security and IAM teams have spent the last decade building real-time Identity and Access Management (IAM) systems. We celebrated instant access decisions, equating speed with security maturity. But the truth is, speed is the new vulnerability, and the ris

A critical LangChain Core vulnerability (CVE-2025-68664, CVSS 9.3) allows secret theft and prompt injection through unsafe serialization; updates fix

Supported now in Cyata for discovery and active posture management. Yes, it took us less than three hours to ship it to production. Antigravity in a sentence Today Google launched Gemini 3 and with it Google Antigravity - an "agent first" coding tool that

Cyata becomes OWASP Corporate Supporter, reinforcing commitment to open security practices as AI agents reshape organizations. Today, Cyata announces its membership as a Corporate Supporter of the Open Web Application Security Project (OWASP). As the worl

Agents Are Acting. Security Isn't Watching. Right now, across your organization, an AI agent is making decisions, accessing systems, and taking actions on behalf of your business. It has no persistent identity. No guardrails. And no one is watching. Accor