Agent-to-Agent Attacks Are Coming: What API Security Teaches Us About Securing AI Systems

AI systems are no longer just isolated models responding to human prompts. In modern production environments, they are increasingly chained together – delegating tasks, calling tools, and coordinating decisions with limited or no human oversight. Almost all that communication happens through APIs...

Security Threat Modeling for Emerging AI-Agent Protocols: A Comparative Analysis of MCP, A2A, Agora, and ANP

The rapid development of the AI agent communication protocols, including the Model Context Protocol MCP, Agent2Agent A2A, Agora, and Agent Network Protocol ANP, is reshaping how AI agents communicate with tools, services, and each other. While these protocols support scalable multi-agent...

A2A-POC

A2A Travel Agency Multi-Agent System A Proof of Concept demon...

From Agent2Agent Prompt Injection to Runtime Self-Defense: How Wallarm Redefines Agentic AI Security

Is an AI-to-AI attack scenario a science fiction possibility only for blockbusters like the Terminator series of movies? Well, maybe not! Researchers recently discovered that one AI agent can “inject malicious instructions into a conversation, hiding them among otherwise benign client requests an...

EUVD-2022-2433

Malicious code in bioql PyPI...

Securing and governing the rise of autonomous agents​​

In this blog, you will hear directly from Corporate Vice President and Deputy Chief Information Security Officer CISO for Identity, Igor Sakhnov, about how to secure and govern autonomous agents. This blog is part of a new ongoing series where our Deputy CISOs share their thoughts on what is most...

Securing and governing the rise of autonomous agents​​

In this blog, you will hear directly from Corporate Vice President and Deputy Chief Information Security Officer CISO for Identity, Igor Sakhnov, about how to secure and govern autonomous agents. This blog is part of a new ongoing series where our Deputy CISOs share their thoughts on what is most...

Towards Unifying Quantitative Security Benchmarking for Multi Agent Systems

Evolving AI systems increasingly deploy multi-agent architectures where autonomous agents collaborate, share information, and delegate tasks through developing protocols. This connectivity, while powerful, introduces novel security risks. One such risk is a cascading risk: a breach in one agent c...

Serverless A2A with Spin

Learn how to build serverless agent-to-agent A2A apps with Spin...

GO-2023-1850 HashiCorp Consul can use cleartext agent-to-agent RPC communication in github.com/hashicorp/consul

HashiCorp Consul can use cleartext agent-to-agent RPC communication in github.com/hashicorp/consul...

Design/Logic Flaw

HashiCorp Consul 1.4.3 lacks server hostname verification for agent-to-agent TLS communication. In other words, the product behaves as if verifyserverhostname were set to false, even when it is actually set to true. This is fixed in 1.4.4...

PT-2019-19855 · Hashicorp +1 · Hashicorp Consul +1

Name of the Vulnerable Software and Affected Versions: HashiCorp Consul version 1.4.3 Description: The issue arises from a lack of server hostname verification for agent-to-agent TLS communication in HashiCorp Consul. This occurs even when the verify server hostname setting is set to true, causin...