Search results for antigravity | Breaking Cybersecurity News | The Hacker News

Cybersecurity researchers have discovered a vulnerability in Google's agentic integrated development environment (IDE), Antigravity, that could be exploited to achieve code execution. The flaw, since patched, combines Antigravity's permitted file-creation capabilities with an insufficient input sanitization in Antigravity's native file-searching tool, find_by_name, to bypass the program's Strict Mode , a restrictive security configuration that limits network access, prevents out-of-workspace writes, and ensures all commands are being run within a sandbox context . "By injecting the -X (exec-batch) flag through the Pattern parameter [in the find_by_name tool], an attacker can force fd to execute arbitrary binaries against workspace files," Pillar Security researcher Dan Lisichkin said in an analysis. "Combined with Antigravity's ability to create files as a permitted action, this enables a full attack chain: stage a malicious script, then trigger ...

Researchers at  Wiz  found that a flaw in six popular AI coding assistants lets a booby-trapped code project quietly take control of a developer's computer. The assistant asks permission to edit one harmless-looking file, but the write lands on a sensitive one instead. The affected tools are Amazon Q Developer, Anthropic's Claude Code, Augment, Cursor, Google Antigravity, and Windsurf. Wiz calls the pattern GhostApproval and published it on July 8. Three of the six have shipped fixes, two have not, and Anthropic disputes that it is a bug. The most exposed are the tools that change files before you can weigh in. How the attack works The attack abuses an old Unix feature called a symbolic link , or symlink , that the assistants fail to check. A symlink quietly points to another file elsewhere on disk, so writing to it actually writes to the target. Wiz built a malicious repository with a symlink named project_settings.json that really points to the victim's ...

Cybersecurity researchers have flagged a new iteration of the GlassWorm campaign that they say represents a "significant escalation" in how it propagates through the Open VSX registry. "Instead of requiring every malicious listing to embed the loader directly, the threat actor is now abusing extensionPack and extensionDependencies to turn initially standalone-looking extensions into transitive delivery vehicles in later updates, allowing a benign-appearing package to begin pulling a separate GlassWorm-linked extension only after trust has already been established," Socket said in a report published Friday. The software supply chain security company said it discovered at least 72 additional malicious Open VSX extensions since January 31, 2026, targeting developers. These extensions mimic widely used developer utilities, including linters and formatters, code runners, and tools for artificial intelligence (AI)-powered coding assistants like Clade Code and Google...

Google deleted three AI agent workflows from its Agent Development Kit (ADK) Python repository. Pillar Security showed that a public GitHub issue could manipulate a triage agent into triggering a privileged code-fixing agent. The researchers said the public agent could be prompt-injected into posting /adk-issue-fix as adk-bot . They identified the bot as a collaborator, so that comment satisfied the privileged workflow's owner, member, or collaborator gate. The trusted bot identity became the authorization bridge. The team demonstrated arbitrary code execution on the continuous integration (CI) runner and exfiltration of the bot personal access token (PAT). The privileged job also held a Google API key and a Google Cloud service-account credential. Its researcher-controlled proof-of-concept attacks do not identify in-the-wild exploitation or a compromised ADK release. The exposed component was the repository automation, not a flaw in the distributed ADK Python package. Fo...

A flaw in four widely used AI coding agents lets someone who controls a plugin's code repository swap the plugin an agent installs for a malicious one, even when the agent locked that plugin to a specific reviewed version, security firm  Air Security said on Thursday . The firm said Anthropic has patched the flaw in Claude Code 2.1.179 and OpenAI in Codex 0.146.0, that GitHub Copilot has no fix, and that Google will not patch the Gemini CLI, which it is retiring. The agents install add-ons called plugins from online marketplaces. To stay safe, a marketplace locks each plugin to a single reviewed version by its commit hash, a long string that identifies an exact snapshot of the code. Air found that the agents fetch that snapshot but never check that the code they end up with actually matches it. A branch is a named line of code in a repository. On a code host that lets someone create a branch whose name is made to look like the commit hash, the owner of a plugin's reposit...

Over 30 security vulnerabilities have been disclosed in various artificial intelligence (AI)-powered Integrated Development Environments (IDEs) that combine prompt injection primitives with legitimate features to achieve data exfiltration and remote code execution. The security shortcomings have been collectively named IDEsaster by security researcher Ari Marzouk (MaccariTA), who discovered them over the last six months. They affect popular IDEs and extensions such as Cursor, Windsurf, Kiro.dev, GitHub Copilot, Zed.dev, Roo Code, Junie, and Cline, among others. Of these, 24 have been assigned CVE identifiers. "I think the fact that multiple universal attack chains affected each and every AI IDE tested is the most surprising finding of this research," Marzouk told The Hacker News. "All AI IDEs (and coding assistants that integrate with them) effectively ignore the base software (IDE) in their threat model. They treat their features as inherently safe because they’ve...

Cybersecurity researchers have flagged dozens of Microsoft Visual Studio Code (VS Code) extensions on the Open VSX repository that are linked to a persistent information-stealing campaign dubbed GlassWorm . The cluster of 73 extensions has been identified as cloned versions of their legitimate counterparts. Of these, six have been confirmed to be malicious, with the remaining acting as seemingly harmless sleeper packages to get users to download them and build trust, before their true intent is manifested through a subsequent update. All the extensions were published at the start of the month, per application security company Socket, which is tracking the latest iteration under the moniker GlassWorm v2 . In total, more than 320 artifacts have been identified since December 21, 2025. The list of extensions identified as malicious is below - outsidestormcommand.monochromator-theme keyacrosslaud.auto-loop-for-antigravity krundoven.ironplc-fast-hub boulderzitunnel.vscode-buddies ...

The internet is noisy this week. We are seeing some wild new tactics, like people using fake cell towers to send scam texts, while some developers are accidentally downloading tools that peek into their private files during a simple install. It is definitely a busy time to be online. Security is always a moving target. Millions of servers are currently sitting online without any passwords, and old software bugs are showing up in the most unexpected places. Even with the right fixes available, staying one step ahead is a full-time job for all of us. Data is shifting in strange ways, too. Some browser tools are now legally selling user history for profit, and new kits are making it simpler for almost anyone to launch a campaign. You have to see these latest updates to believe them. Let’s look at the full list... SMS blaster phishing crackdown Canadian Authorities Arrest 3 Men for Alleged Use of SMS Blaster Canadian authorities have ar...

Hey @BarackObama ! Please don't extradite Gary McKinnon Gary McKinnon,  a Scottish systems administrator and hacker who has been accused of what one U.S. prosecutor claims is the " biggest military computer hack of all time " by hacking into the Pentagon, faces an ordeal of terrifying brutality if he is extradited to the United States. America wants to put him on trial, and if tried there he could face 60 years behind bars. Note : Request to Every Reader ! Please Re-Tweet/Share this article if you want to Support Gary McKinnon in the fight for justice. The mother Gary McKinnon has called for her son to stand trial in Britain claiming attempts to extradite him to the US have destroyed his life. He claims his motivation, drawn from a statement made before the Washington Press Club on 9 May 2001 by " The Disclosure Project ", was to find evidence of UFOs, antigravity technology, and the suppression of " free energy ", all of which he claims to have ...

Ask an AI agent to summarize the reviews on a product page, and a single planted review can make it click "Buy Now" instead. Ask a coding assistant to apply a maintainer's fix from a GitHub thread, and a fake comment can make it run a stranger's command on your computer. Neither trick hijacks the agent's task. Each one just corrupts the facts it trusts and lets it carry on with the job you asked for. That is the shape of a new class of attack laid out in a  paper posted July 6  by researchers from Seoul National University, the University of Illinois Urbana-Champaign, and Largosoft. They call it agent data injection , or ADI. The attacker's input gets dressed up as data the agent already trusts, like a sender's name or a button's ID, so it slips past most of the defenses built to stop prompt injection. The gap comes from how an agent reads. It takes in two kinds of things: instructions, meaning what you and the app's developer tell it to d...

Popular artificial intelligence (AI)-powered Microsoft Visual Studio Code (VS Code) forks such as Cursor, Windsurf, Google Antigravity, and Trae have been found to recommend extensions that are non-existent in the Open VSX registry, potentially opening the door to supply chain risks when bad actors publish malicious packages under those names. The problem, according to Koi , is that these integrated development environments (IDEs) inherit the list of officially recommended extensions from Microsoft's extensions marketplace. These extensions don't exist in Open VSX. The VS Code extension recommendations can take two different forms: file-based, which are displayed as toast notifications when users open a file in specific formats, or software-based, which are suggested when certain programs are already installed on the host. "The problem: these recommended extensions didn't exist on Open VSX," Koi security researcher Oren Yomtov said. "The namespaces were u...

Cybersecurity researchers have disclosed details of a new attack method dubbed Reprompt that could allow bad actors to exfiltrate sensitive data from artificial intelligence (AI) chatbots like Microsoft Copilot in a single click, while bypassing enterprise security controls entirely. "Only a single click on a legitimate Microsoft link is required to compromise victims," Varonis security researcher Dolev Taler said in a report published Wednesday. "No plugins, no user interaction with Copilot." "The attacker maintains control even when the Copilot chat is closed, allowing the victim's session to be silently exfiltrated with no interaction beyond that first click." Following responsible disclosure, Microsoft has addressed the security issue. The attack does not affect enterprise customers using Microsoft 365 Copilot. At a high level, Reprompt employs three techniques to achieve a data‑exfiltration chain - Using the "q" URL parameter in...

Bad week. Turns out the easiest way to get hacked in 2026 is still the same old garbage: shady packages, fake apps, forgotten DNS junk, scam ads, and stolen logins getting dumped into Discord channels like it’s normal. Some of these attack chains don’t even feel sophisticated anymore. More like some tired guy with a Telegram account and too much free time. The worst part is how often this stuff still works. Meanwhile, AI tools are speeding up exploit hunting, browsers are keeping passwords sitting in memory for “performance reasons,” and even ransomware crews are pushing broken builds into the wild. Everybody’s scrambling to patch faster because attackers are automating faster. Anyway. ThreatsDay’s rough this week. Let’s get into it. Credential theft campaign New MicroStealer Spotted A new stealer called MicroStealer has been observed targeting education and telecom sectors to steal sensitive data. It was first observed in the wild in...

An update on Athena, and some unsolicited predictions on what's coming next On Saturday, Dario Amodei published We Must Pace the Frontier . I agree with him. Go read it if you haven't. I've spent the summer looking at what these models find, and the gap he describes between what they can do and what the rest of us are ready for is the one I've been staring at since May. The hardest piece of his plan is the one that asks governments to coordinate. They're in a difficult spot: regulate too little and a US company accidentally builds the weapon, regulate too much and it gets built somewhere else, and open source isn't governable either way. Where governments can act is on consumption: not what the models can do, but what happens to what they find. Who gets a vulnerability first, how fast a fix reaches the people running the code, whether the operators who can't move on an attacker's timeline get a head start. That's what Gold Eagle is. It matters...

It’s Monday again. This week’s threat list looks painfully familiar: abused integrations, fake tools, poisoned websites, ransomware crews trying to shut down security tools, and mobile malware asking for way too much control. The annoying part is how little of this feels new. Weak credentials, sketchy downloads, browser extensions with too much access, and WordPress sites are used to push more attacks. Nothing clever. Just sloppy, cheap, and effective. Here’s the Monday recap. Let’s get into the week’s mess. ⚡ Threat of the Week FortiBleed Campaign Identifies Over 80K Targets — A large-scale campaign codenamed FortiBleed has systematically targeted and compromised Fortinet FortiGate firewall and SSL VPN gateway devices worldwide. According to SOCRadar, it has been running since at least February 2026, with over 80,000 devices identified with working usernames and passwords that have been tested by suspected Russian-speaking threat actors using automated tools running around...