'Ghostcommit' hides prompt injection in images to fool AI agents, steal secrets

A PNG hiding a prompt injection could steal your repo's secrets, researchers demonstrate. The technique, dubbed 'Ghostcommit, ...
SiliconANGLE

Snyk launches Evo Agentic Development Security to police AI coding agents

Cybersecurity company Snyk Ltd. today launched Evo Agentic Development Security, a new layer of its artificial intelligence security platform built to police the autonomous coding agents that ...
The Verge

Read this before you vibe-code another app

Bob Starr was delighted with his vibe-coded website. “Boomberg” showed how much US tax money is going to tech companies, and Starr launched it online immediately after making it. It wasn’t until ...
Geeky Gadgets

Full Vibe Coding Tutorial : Build Custom Apps Quickly

Vibe coding is a structured approach to building custom applications that combine ease of use with advanced capabilities. As explained by Zinho Automates, this method emphasizes practical ...
Hosted on MSN

Inside NASA’s most secure lab

A look inside one of NASA’s most protected laboratories and the work being done there. US launches new Iran strikes after Trump announces toll on Strait of Hormuz Coffee linked to significant new side ...
CNBC

OpenAI to acquire Ona to support its AI coding assistant, Codex

OpenAI announced it will acquire Ona, a startup that provides cloud environments for AI agents. Ona's technology will allow OpenAI's coding assistant, Codex, to take on longer-running tasks, OpenAI ...
SDxCentral

Broadcom injects security updates into Spring, Java ecosystems

Broadcom rolled out security updates to the Spring and Java ecosystems tied to helping organizations navigate a surge in AI-detected security threats. The updates are through Broadcom’s Tanzu business ...
CSOonline

Claude Code has an MCP security problem — and your developers are already using it

Claude Code is Anthropic’s AI coding assistant — a command-line tool that developers are adopting fast. It connects to external services through Model Context Protocol, the standard that lets AI tools ...
Los Angeles Times

Missing worker at high-security lab in New Mexico found dead in remote forest

This is read by an automated voice. Please report any issues or inconsistencies here. See more from the L.A. Times in Google Search. Set us as preferred Human remains found beside a handgun in a ...
Morningstar

Salt Security launches Salt Code, the first agentic security solution to enforce security policies inside AI coding assistants

The first solution that enforces security policy inside every AI coding assistant your developers use. Claude, Cursor, GitHub Copilot, Windsurf, Codex and Gemini CLI now generate policy-compliant code ...
Ars Technica

Fed up with vibe coders, dev sneaks data-nuking prompt injection into their code

The controversy over vibe coding reached a new high this week after a developer added hidden instructions to his open source Java testing app to sabotage projects performed by AI coding agents. The ...
Business Wire

Detectify Launches MCP Server to Secure the Autonomous Coding Loop

As AI agents take over the software lifecycle, Detectify embeds continuous, autonomous security validation directly into AI-driven development workflows STOCKHOLM--(BUSINESS WIRE)--Detectify, the ...