Trending...
- California: Governor Newsom issues emergency proclamations to support recovery in Humboldt and Imperial counties - 115
- California: Governor Newsom announces nearly $1.3 billion for cleaner transportation, stronger transit connections - 114
- As Trump leaves America's seat empty, Governor Newsom leads California delegation to UN climate summit in Türkiye - 108
New LLM runtime protection connects prompt injection to downstream MCP and API attacks, while helping enterprises close gaps in existing AI protection
PALO ALTO, Calif. - Californer -- Salt Security, the leader in agentic and API security, today announced native AI Detection and Response (AI-DR) capabilities within the Salt Agentic Security Platform.
The new capabilities provide real-time LLM protection against direct and indirect prompt injection, jailbreak attempts, unsafe model behavior, and other runtime threats. Prompt injection is the top-ranked risk in the OWASP Top 10 for LLM Applications 2026, and it takes two forms, direct and indirect, both of which the new capabilities detect in real time. Salt also brings the AI guardrails and gateways enterprises already use into one security view, helping teams apply consistent protection across models, agents, MCP servers, tools, and downstream APIs.
Protecting the full agentic path
AI agents connect models to tools and business systems. An attack that starts with a malicious prompt can expose those connections and lead to unauthorized access or actions downstream. This is not hypothetical: in Salt Security's 2H 2026 State of Agentic AI and API Security survey, nearly half of organizations (49.8%) confirmed or suspected that an AI agent took an action they did not intend, expect, or authorize in the past year, and only 12.5% can consistently trace an agent's full path from the initial prompt through the MCP servers and APIs it reaches. Security teams need to see how an attack moves across these layers to understand what is at risk.
More on The Californer
AI-DR is built into Salt Agentic Detection and Response (AG-DR), extending its runtime protection to the LLM layer. The Salt Agentic Security Graph connects agents to their models, Model Context Protocol (MCP) servers, tools, and downstream APIs. With native AI-DR, teams can connect an attack against the model to subsequent MCP and API attacks in the same platform.
AG-DR and Agentic Security Posture Management (AG-SPM) form the Salt Agentic Security Platform. AG-SPM helps teams understand their agents and security gaps, while AG-DR detects and connects attacks across those agents and the systems they use.
Seeing how AI attacks reach business systems
For example, an attacker could trick a billing agent into revealing information about a refund tool on an MCP server and the API behind it. The attacker could then exploit that API - directly or through the agent to attempt unauthorized refunds. What began as a malicious prompt has become an attack on a payment system.
Salt shows these steps together, from the prompt injection through the MCP server to the API attack. Security teams can see how the attack started, what it targeted, and which business systems are at risk, even when the attacker moves beyond the agent to attack an API directly.
Unified Visibility Across AI Guardrails and Native Protection Where Coverage Is Missing
Enterprises use AI guardrails across cloud platforms, endpoint and SASE solutions, AI gateways, and managed AI services. Each control protects the interactions it covers, leaving teams to identify inconsistencies and gaps across environments.
More on The Californer
Through AG-SPM and the Agentic Security Graph, Salt gives teams one view of these guardrail configurations and the agents they protect. Where protection is missing, including in homegrown agents running in Kubernetes, Salt can fill the gap with native AI-DR within AG-DR. Customers can establish more consistent protection while keeping their existing gateways and security products.
"An attack on an AI model can become an attack on the systems that run the business," said Roey Eliyahu, co-founder and CEO of Salt Security. "Our native AI-DR protects LLM interactions and connects what happens at the model to the tools and APIs downstream. Teams can see the full attack, understand what is at risk, and fill protection gaps while keeping the guardrails they already use."
Availability
Native AI-DR capabilities are available within Salt AG-DR as part of the Salt Agentic Security Platform. Visit salt.security/demo-request for more information.
About Salt Security
Salt Security is the leader in agentic and API security, protecting the world's most innovative enterprises from AI agent and API attacks. AI is shifting from chatbots that answer to agents that act, and Salt secures the entire agentic path, from AI-generated code to runtime, across models, MCP servers, tools, and downstream APIs. Founded in 2016, Salt Security is backed by Sequoia Capital, S Capital, Tenaya Capital, Salesforce Ventures, Advent International, and other leading investors. For more information, visit salt.security.
The new capabilities provide real-time LLM protection against direct and indirect prompt injection, jailbreak attempts, unsafe model behavior, and other runtime threats. Prompt injection is the top-ranked risk in the OWASP Top 10 for LLM Applications 2026, and it takes two forms, direct and indirect, both of which the new capabilities detect in real time. Salt also brings the AI guardrails and gateways enterprises already use into one security view, helping teams apply consistent protection across models, agents, MCP servers, tools, and downstream APIs.
Protecting the full agentic path
AI agents connect models to tools and business systems. An attack that starts with a malicious prompt can expose those connections and lead to unauthorized access or actions downstream. This is not hypothetical: in Salt Security's 2H 2026 State of Agentic AI and API Security survey, nearly half of organizations (49.8%) confirmed or suspected that an AI agent took an action they did not intend, expect, or authorize in the past year, and only 12.5% can consistently trace an agent's full path from the initial prompt through the MCP servers and APIs it reaches. Security teams need to see how an attack moves across these layers to understand what is at risk.
More on The Californer
- Chargezen opens its revenue ops platform to AI assistants and personal agents
- Pibit Joins Guidewire PartnerConnect, Bringing Risk-Scored Submissions to PolicyCenter
- Turkish Engineer Who Cracked Wall Street's Algorithm Launches Hermes AI Analyzer
- UK Financial Ltd Launches MayaSwap On MAYA CHAIN To Facilitate UKFLMS-For-Gold Swaps, Officially Transforming UKFLMS From Meme Into A Real-World Asset
- Resident Evil's Wesker Is Now Beavis's "Bold New Voice" on Mike Judge's Beavis & Butt-Head
AI-DR is built into Salt Agentic Detection and Response (AG-DR), extending its runtime protection to the LLM layer. The Salt Agentic Security Graph connects agents to their models, Model Context Protocol (MCP) servers, tools, and downstream APIs. With native AI-DR, teams can connect an attack against the model to subsequent MCP and API attacks in the same platform.
AG-DR and Agentic Security Posture Management (AG-SPM) form the Salt Agentic Security Platform. AG-SPM helps teams understand their agents and security gaps, while AG-DR detects and connects attacks across those agents and the systems they use.
Seeing how AI attacks reach business systems
For example, an attacker could trick a billing agent into revealing information about a refund tool on an MCP server and the API behind it. The attacker could then exploit that API - directly or through the agent to attempt unauthorized refunds. What began as a malicious prompt has become an attack on a payment system.
Salt shows these steps together, from the prompt injection through the MCP server to the API attack. Security teams can see how the attack started, what it targeted, and which business systems are at risk, even when the attacker moves beyond the agent to attack an API directly.
Unified Visibility Across AI Guardrails and Native Protection Where Coverage Is Missing
Enterprises use AI guardrails across cloud platforms, endpoint and SASE solutions, AI gateways, and managed AI services. Each control protects the interactions it covers, leaving teams to identify inconsistencies and gaps across environments.
More on The Californer
- Hotels near LAX after the FAA ground stop: 4 South Bay hotels with free breakfast, kitchens and parking
- Pleasanton Welcomes The Great Junk Hunt – Discover Unique Vintage Treasures and Holiday Finds!
- Nine Platinum Honors Lead Scientology Media Productions' 12 Wins at 2026 MarCom Awards
- Flash Tower Launches AI Security Platform to Help Businesses See What Their AI Can Access
- Entrepreneur Nouho M Kanneh Talks Family, Faith and a $37 Million Portfolio in New Interview
Through AG-SPM and the Agentic Security Graph, Salt gives teams one view of these guardrail configurations and the agents they protect. Where protection is missing, including in homegrown agents running in Kubernetes, Salt can fill the gap with native AI-DR within AG-DR. Customers can establish more consistent protection while keeping their existing gateways and security products.
"An attack on an AI model can become an attack on the systems that run the business," said Roey Eliyahu, co-founder and CEO of Salt Security. "Our native AI-DR protects LLM interactions and connects what happens at the model to the tools and APIs downstream. Teams can see the full attack, understand what is at risk, and fill protection gaps while keeping the guardrails they already use."
Availability
Native AI-DR capabilities are available within Salt AG-DR as part of the Salt Agentic Security Platform. Visit salt.security/demo-request for more information.
About Salt Security
Salt Security is the leader in agentic and API security, protecting the world's most innovative enterprises from AI agent and API attacks. AI is shifting from chatbots that answer to agents that act, and Salt secures the entire agentic path, from AI-generated code to runtime, across models, MCP servers, tools, and downstream APIs. Founded in 2016, Salt Security is backed by Sequoia Capital, S Capital, Tenaya Capital, Salesforce Ventures, Advent International, and other leading investors. For more information, visit salt.security.
Source: Salt Security
0 Comments
Latest on The Californer
- Massive Acquisition Into Defense With STS for Virtuix Holdings; $40 Million Revenue Business Will Accelerate Growth Transforming Market Position
- Get Care at Home Sponsors Citrus Heights HART's 2026 Spaghetti Fest
- Orlando Real Estate Broker Bent Danholm Wins 2026 Goody Business Book Award for The Architecture of Demand
- Commercial Sales for U.S.-Made, Preservative-Free Ketamine Amid Long-Runnin Shortage Following FDA Approval by NRx Pharmaceuticals, Inc
- The King Returns: Satirical December 2026 Rematch Sees Challenger Delayed by a Christmas Light Installation
- Elevate Your Everyday Style with Designer Earrings and Luxury Designs
- LCH2 Awarded Additional $1 Million to Advance Lewis County Clean Energy Campus
- Governor Newsom announces California's first Environmental Youth Advisory Council, empowering the next generation of climate leaders
- Security Planning Tips For Your Holiday Event From Access Patrol Services
- Is That Coaching Program Really a Ponzi Scheme?
- Governor Newsom, First Partner Siebel Newsom unveil 20th class of California Hall of Fame
- Apple Valley Home Prices Rise 12% to $461,500 in October 2026 as Closed Sales Decline 12.9%
- Travel Deals For Solo Women Announced - Morocco and Costa Rica
- Volunteer Opportunities At Southeast Ventura County YMCA
- Developer Daniel Kaufman Says Voters Paid for Housing but Kept the Rules That Slow It Down
- Contracting Resources Group Receives 2026 HIRE Vets Platinum Medallion Award
- NursingColleges.com Announces Jesutofunmi Oluwaleke as 2026 Scholarship Winner
- THE DASH CAM: THINKWARE Announces Black Friday Offers
- Business News & Info Goes Inside Paragon FX Group's Hunt for Original Film Props
- Las Vegas Comedy Headliner Don Barnhart Returns to Pechanga Thanksgiving Weekend Nov. 27–28
