Back securityweekly.com

Akto

securityweekly.com • June 22, 2026

Akto is the trusted MCP and AI Agent Security Platform for Fortune 500 security teams.

Akto Atlas for Employees

Akto Argus for Homegrown Apps

Get visibility and enforce guardrails for LLMs, AI agents, and MCP tools used by employees across their devices, ensuring safe AI usage at the individual level.

Turn AI chaos into control. Akto maps every AI agent and MCP tool, gives visibility, runs continuous red teaming, and enforces guardrails at scale.

Automatically discover and catalog MCPs, AI agents, tools, and resources across your infrastructure, cloud, employee laptops.

Security leaders rank MCP/agent discovery as a critical need

better Agentic actions visibility Coverage

AI Agent–tool actions analyzed and secured with guardrails

concern of Enterprises while deploying AI agents in production is cybersecurity risk.

Without Akto, hidden risks at input, execution, and output turn trust into an illusion.

Attackers compromise MCP-connected tools to manipulate agent behavior, extract context, or return malicious outputs.

Malicious inputs trick agents into skipping validation steps and jumping directly to sensitive tool execution.

Malicious or unauthorized tools impersonate legitimate ones to hijack execution within MCP-based workflows.

LLMs misinterpret untrusted tool responses as prompts, allowing attackers to influence or control model behavior.

LLMs invoke backend actions they should not, due to missing or bypassed authorization checks.

Backends change tool behavior mid-session, breaking trust assumptions and enabling unexpected execution paths.

Attackers compromise MCP-connected tools to manipulate agent behavior, extract context, or return malicious outputs.

Malicious inputs trick agents into skipping validation steps and jumping directly to sensitive tool execution.

Malicious or unauthorized tools impersonate legitimate ones to hijack execution within MCP-based workflows.

Securing LLMs with a 3-Layer Defense Model

Cheatsheet on Building Safe and Governed AI Agents

The Essential Agentic AI Security Glossary

The full story

This article is one source in a clustered incident — the cluster page carries the summary, timeline and every other outlet covering it.

Akto Enhances AI Agent Security with New Partnerships Amid Rising Cyber Threats On April 23, 2026, Akto announced partnerships with several AI infrastructure providers to enhance security for AI agents deployed in enterprise environments. The partnerships aim to address the significant cybersecurity risks associated with AI agent operations, where 79% of enterprises report limited visibility into AI agent activities. The integrations with Portkey, TrueFoundry, Arcade.dev, LiteLLM, and LangChain will embed runtime security measures directly into existing AI frameworks, preventing issues like prompt injection and sensitive data leakage. Akto's CEO emphasized the necessity of integrating security into development processes rather than as an afterthought. The partnerships are a response to increasing concerns over malicious inputs and unauthorized tool access that could compromise AI agent behavior and data integrity. Akto's solutions will provide continuous monitoring and enforcement of security policies across AI deployments, ensuring safer usage of AI technologies. The current status reflects a proactive approach to mitigating risks associated with AI agent deployments. 2 sources 55

Extracted Entities

Platforms (2)

Akto AWS Bedrock