Spring Office Hours Podcast: S5E18 - The Latest from OpenAI, Anthropic and Spring AI 2.0

Join Dan Vega and DaShaun Carter for the latest updates from the Spring Ecosystem. In this episode, Dan and DaShaun catch up on the fast moving world of AI and what it means for Java developers. The guys will cover recent releases from OpenAI and Anthropic, then dig into Spring AI 2.0, which is n...

PYSEC-2026-2000 Universal Tool Calling Protocol (UTCP) client library for Python vulnerable to Trust Boundary Violation through Manual JSON specification

The vulnerability arises when a client fetches a tools’ JSON specification, known as a Manual, from a remote Manual Endpoint. While a provider may initially serve a benign manual e.g., one defining an HTTP tool call, earning the clients’ trust, a malicious provider can later change the manual to...

This Week in Spring - June 16th, 2026

Hi Spring fans! Welcome to another installment of This Week in Spring! I'm writing this from the oh-so-delightful and delicious! city of New Delhi, India. It's been a real privilege to come and visit so many amazing people. Last night my friend DaShaun and I presented here at the local Delhi JUG,...

CVE-2026-12210

A vulnerability was detected in universal-tool-calling-protocol python-utcp 1.1.0. This affects an unknown function of the component utcp-gql/utcp-websocket. Performing a manipulation results in server-side request forgery. The attack can be initiated remotely. The exploit is now public and may b...

CVE-2026-12210

CVE-2026-12210 affects the universal-tool-calling-protocol project, specifically the python-utcp 1.1.0 release, with a vulnerability in the utcp-gql/utcp-websocket component that enables server-side request forgery. The description notes a remote, public exploit and a lack of vendor response. The...

PT-2026-49172

A vulnerability was detected in universal-tool-calling-protocol python-utcp 1.1.0. This affects an unknown function of the component utcp-gql/utcp-websocket. Performing a manipulation results in server-side request forgery. The attack can be initiated remotely. The exploit is now public and may b...

Tool Calling in Spring AI 2.0: A Composable, Agentic Architecture

Tool calling — the ability for an AI model to invoke application-defined functions and act on the results — is the essential building block of agentic AI systems. A model that can discover information, take action, and loop until a goal is reached is an agent. Spring AI 2.0 rearchitects tool...

Universal Tool Calling Protocol 操作系统命令注入漏洞

Universal Tool Calling Protocol is an official Python implementation of the UTCP open-source protocol. Versions prior to 1.1.3 of Universal Tool Calling Protocol contained a vulnerability related to operating system command injection. This vulnerability stemmed from the substituteutcpargs method...

Universal Tool Calling Protocol 安全漏洞

Universal Tool Calling Protocol is an official Python implementation of the UTCP open-source protocol. Versions prior to 1.1.3 of Universal Tool Calling Protocol contained security vulnerabilities; these vulnerabilities stemmed from the prepareenvironment method passing complete environment...

Universal Tool Calling Protocol 代码问题漏洞

Universal Tool Calling Protocol is an official Python implementation of the UTCP open-source protocol. Versions prior to 1.1.3 of Universal Tool Calling Protocol had code vulnerabilities, which stemmed from inconsistent trust boundaries and could lead to man-in-the-middle server request forgery...

OrchJail: Jailbreaking Tool-Calling Text-To-Image Agents by Orchestration-Guided Fuzzing

Tool-calling text-to-image T2I agents can plan and execute multi-step tool chains to accomplish complex generation and editing queries. However, this capability introduces a new safety attack surface: harmful outputs may arise from tool orchestration, where individually benign steps combine into...

Your Agent Is More Brittle Than You Think: Uncovering Indirect Injection Vulnerabilities in Agentic LLMs

The rapid deployment of open-source frameworks has significantly advanced the development of modern multi-agent systems. However, expanded action spaces, including uncontrolled privilege exposure and hidden inter-system interactions, pose severe security challenges. Specifically, Indirect Prompt...

Trust Boundary Violation

Overview utcp is an Universal Tool Calling Protocol UTCP client library for Python Affected versions of this package are vulnerable to Trust Boundary Violation. Via the remote Manual Endpoint, the client retrieves a tool’s JSON specification, known as a Manual. An attacker can execute arbitrary...

Universal Tool Calling Protocol 安全漏洞

Universal Tool Calling Protocol is an official python implementation library for UTCP in the Universal Tool Calling Protocol open source. A security vulnerability exists in Universal Tool Calling Protocol that originates when a client obtains the JSON specification of a tool from a remote Manual...

Smart Tool Selection: Achieving 34-64% Token Savings with Spring AI's Dynamic Tool Discovery

As AI agents connect to more services—Slack, GitHub, Jira, MCP servers—tool libraries grow rapidly. A typical multi-server setup can easily have 50+ tools consuming 55,000+ tokens before any conversation starts. Worse, tool selection accuracy degrades when models face 30+ similarly-named tools. T...

Beyond JSON: Converting Spring AI Tool Response Formats to TOON, XML, CSV, YAML, ...

JSON is the go-to format for LLM tool responses, but recent discussions around alternative formats like TOON Token-Oriented Object Notation claim potential benefits in token efficiency and performance. While the debate continues—with critical analyses pointing to context-dependent results—the...

Exploiting Web Search Tools of AI Agents for Data Exfiltration

Large language models LLMs are now routinely used to autonomously execute complex tasks, from natural language processing to dynamic workflows like web searches. The usage of tool-calling and Retrieval Augmented Generation RAG allows LLMs to process and retrieve sensitive corporate data, amplifyi...

Mind the Gap: Evaluating Model- and Agentic-Level Vulnerabilities in LLMs with Action Graphs

As large language models transition to agentic systems, current safety evaluation frameworks face critical gaps in assessing deployment-specific risks. We introduce AgentSeer, an observability-based evaluation framework that decomposes agentic executions into granular action and component graphs,...

DoomArena: a Framework for Testing AI Agents against Evolving Security Threats

We present DoomArena, a security evaluation framework for AI agents. DoomArena is designed on three principles: 1 It is a plug-in framework and integrates easily into realistic agentic frameworks like BrowserGym for web agents and $τ$-bench for tool calling agents; 2 It is configurable and allows...