Salt Security

@SaltSecurity

Securing the Agentic AI action layer: protecting the APIs, MCP servers, and agents powering modern digital business.

Palo Alto, CA

salt.security

Joined August 2018

Pinned
Salt Security
@SaltSecurity
Apr 8
BIG NEWS! Salt Security’s 1H 2026 State of AI and API Security report just dropped! 🙌 Are you up to date on your AI/API security insights? Bottom line: You can’t secure AI without securing the APIs that power it. Download the report: content.salt.security/State-of-AI-AP… Read the blog:
Salt Security
@SaltSecurity
13h
An AI agent was asked to book a gym class, and instead it found and exploited a BOLA flaw in the API and canceled another user's waitlist spot 🫣 No malicious intent, just optimization. This is a textbook OWASP API1 (Broken Object Level Authorization) violation. Salt
Claude-Powered AI Agent Exploits API Authorization Flaw to Hack Gym Booking System
From gbhackers.com
Salt Security
@SaltSecurity
Aug 7
That’s a wrap on Black Hat USA 2026! We’re leaving Vegas with a lot to celebrate 🧂🏆 From packed conversations and live demos to diving deep into the future of AI, APIs, and Agentic Security, this week was all about connecting with the people shaping what’s next in
Salt Security
@SaltSecurity
Aug 6
What is agentic AI governance and why does it matter? It’s how organizations keep autonomous AI agents visible, controlled, secure, and accountable as they access data, invoke tools, call APIs, and act at machine speed. Our new guide explores how to build an effective agentic AI
Agentic AI Governance Guide: Best Practices for Security
From salt.security
Salt Security
@SaltSecurity
Aug 5
UK gov tested frontier AI agents. They made unauthorized API calls, forged identities, and tried to deceive real humans unprompted. 19 rogue actions in a "controlled" eval. Your prod agents have more access. More info 👇 @CNN: cnn.com/2026/08/04/tec… @TheManilaTimes:
AI agents fake identities, target real people in new security incident | CNN Business
From cnn.com