Google ADK flaws reveal what happens when AI agents trust the wrong message
“For CISOs, materiality should be determined by tracing three things,” said Grover. “First, which agents consume untrusted content such as pull requests, issues, emails, support tickets, or external documents? Second, can the output of those agents directly or indirectly trigger…
Microsoft Azure Cosmos DB key leak flaw patched before exploitation
Microsoft has had a narrow escape from total embarrassment: A security company uncovered a critical vulnerability that could have compromised all Azure Cosmos DB databases — both those of customers and Microsoft’s own. Google subsidiary Wiz found a flaw in…
Critical Ruflo flaw lets attackers hijack AI agents through exposed MCP bridge
The researchers said the bridge’s /mcp endpoint accepts tool invocations without authentication. In a proof-of-concept demonstration, they used Ruflo’s terminal_execute tool to obtain command execution inside the container with a single HTTP request. “Because the MCP Bridge requires direct access to the…
Kotlin beta previews support for coroutine stack trace recovery
Kotlin 2.4.20-Beta2 introduces support for coroutine stack trace recovery, with the addition of the StackTraceRecoverable interface to the standard library. This feature, currently experimental, improves integration with the kotlinx.coroutines library because it allows developers to create new exception instances for stack trace recovery without…
Model Context Protocol is going stateless to make scaling simpler
“When your infrastructure team asks whether MCP services can scale like other cloud applications, the answer used to be ‘not quite.’ With the move to a stateless architecture, the answer is now yes,” Bandta added. Earlier versions of the protocol…
Oracle issues critical patches for Database Server, Fusion Middleware
Oracle’s July 2026 Critical Patch Update, its largest ever, contains 1,449 new security patches spanning 32 product families, from Oracle Database and E-Business Suite to PeopleSoft, GoldenGate, Java SE, and Fusion Middleware. Fusion Middleware was particularly hard hit, with new…
AI OK in Linux development, says Torvalds
“It can also be a somewhat painful tool, both for maintainer workloads and just from a ‘it keeps finding embarrassing bugs’ standpoint,” he said of the use of AI in security scanning. “The solution is to make sure those LLM…
OpenAI’s new hardware is a $230, 13-switch keyboard for Codex
OpenAI is selling its first hardware — without any help from Jony Ive. It describes the Codex Micro as a “command center for agentic work” but it’s really a 13-switch wireless keyboard customized to help developers keep tabs on what…
How to use virtual environments in Python
Using Python virtual environments with Jupyter notebooks If you’re using Jupyter notebooks (aka IPython notebooks), and you already have Jupyter installed systemwide, create your virtual environment and activate it. Then, from your virtual environment directory, run pip install ipykernel to…
CrowdStrike identifies five new AI prompt injection threats
Unwitting User Context-Data Injection, an exploit that draws on the boundary between trusted data and executable instructions, tricking the user into introducing malicious instructions as part of the context data for the LLM. The prompt may be harmless: The malicious…
