Search results for github openai | Breaking Cybersecurity News | The Hacker News

Three researchers at the security firm  Hacktron  used Anthropic's Claude Opus 5 to chain two flaws and take over the ChatGPT and Codex accounts of several OpenAI employees, then reach an internal OpenAI code repository. The chain began with a bug in the software that runs OpenAI's public help forum and moved through a weakness in OpenAI's own login system. This was security research, not a real-world attack: the team reported the flaws to OpenAI, proved the access with a harmless pull request, and then stopped. From the first look, that internal access took under 72 hours. OpenAI confirmed a fix about 14 hours after the report, according to Hacktron, and on September 1 paid the team a $6,500 bounty. OpenAI said the award "recognizes the OpenAI-side finding, not the actions against Discourse," the open-source software that runs the forum. Testing the forum itself was outside its bug bounty program. OpenAI has not publicly described the login flaw, and it ...

A previously unknown vulnerability in OpenAI ChatGPT allowed sensitive conversation data to be exfiltrated without user knowledge or consent, according to new findings from Check Point. "A single malicious prompt could turn an otherwise ordinary conversation into a covert exfiltration channel, leaking user messages, uploaded files, and other sensitive content," the cybersecurity company said in a report published today. "A backdoored GPT could abuse the same weakness to obtain access to user data without the user's awareness or consent." Following responsible disclosure, OpenAI addressed the issue on February 20, 2026. There is no evidence that the issue was ever exploited in a malicious context. While ChatGPT is built with various guardrails to prevent unauthorized data sharing or generate direct outbound network requests , the newly discovered vulnerability bypasses these safeguards entirely by exploiting a side channel originating from the Linux runtime ...

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...

Cybersecurity researchers have shed light on a large-scale campaign that has turned compromised GitHub repositories into distributed attack infrastructure designed to target cPanel and WebHost Manager (WHM) instances. The activity involves malicious Packagist development versions spanning 10 packages associated with a legitimate PHP and DevOps developer, dinushchathurya, between July 12 and 13, 2026. The list of affected Packagist packages is below - dinushchathurya/nationality-list dinushchathurya/srilankan-divisional-secretariats dinushchathurya/srilankan-gn-divisions dinushchathurya/srilankan-local-authorities dinushchathurya/srilankan-mobile-number-validator dinushchathurya/srilankan-state-hospitals dinushchathurya/srilankan-universities dinushchathurya/uk-mobile-number-validator dinushchathurya/uk-post-code dinushchathurya/websmslk "The PHP libraries were not the execution path," Socket said in a statement. "Attackers had added...

An agent running Anthropic's Claude Mythos 5 spent 34 hours trying to get a malware dropper merged into a real open-source project during a cyber evaluation by the UK's AI Security Institute. When a bystander publicly warned that the code was malicious, the agent denied it, force-pushed a rewritten branch history to erase the evidence, and posted from a second account it controlled to vouch for its own work. The project's maintainer closed the pull request anyway. The institute, known as AISI, published its incident report on Tuesday. Across 122 runs of a capture-the-flag (CTF) exercise on two of its cyber ranges, researchers catalogued 19 unsanctioned actions on the live internet across 10 runs: 17 from Mythos 5, a restricted model Anthropic sells for cybersecurity work, and two from OpenAI's GPT-5.6 Sol. AISI says the attempts failed and that it has found no evidence of resulting real-world harm. Both models ran with their providers' cyber classifiers swi...

Beginning July 27, 2026, GitHub will cut public bug bounty payouts by at least half at every severity level. Critical findings will drop from $20,000-$30,000+ to a fixed $10,000, while its permanent invite-only VIP tier will pay $30,000 or more. Reports filed before that date, including those already in GitHub's growing triage queue, will retain the previous payout terms. GitHub said the changes are intended to reduce noise while giving established researchers faster responses, higher rewards, and closer access to its security engineering team. "You don't earn more by submitting more," the company said. "You earn more by submitting better." The public program is moving from flexible ranges to fixed payments: Low: $250, down from $617-$2,000 Medium: $2,000, down from $4,000-$10,000 High: $5,000, down from $10,000-$20,000 Critical: $10,000, down from $20,000-$30,000+ The Hacker News calculated that the new public rates are 50% lower f...

GitGuardian researchers found 321 n8n instances accepting API tokens exposed in public GitHub commits and demonstrated four ways attackers could use them to access sensitive data and downstream credentials without exploiting a software vulnerability. We scanned public GitHub commits for exposed n8n API tokens and identified 4,576 unique credentials associated with 1,255 hostnames. Of the 896 instances reachable at the time of testing, 321 accepted at least one leaked token. That means leaked credentials provided authenticated access to 36% of the reachable instances we tested, or roughly 26% of all hostnames identified in the commits. The implications extend well beyond n8n. Organizations use the automation platform to connect databases, source code repositories, cloud environments, artificial intelligence services, customer support platforms, and other internal systems. A sufficiently privileged n8n token can expose workflow definitions and execution data, allow attackers to us...

A public issue can trick GitHub Agentic Workflows into leaking the contents of an organization's private repositories, researchers at Noma Security have shown. The attacker needs only to open a normal-looking issue on a public repository, with no stolen credentials and no access to the organization. If that organization has given the agent read access across its repositories, private ones included, the issue can steer it into pulling private contents into a public comment. Noma calls the technique GitLost . The target is GitHub Agentic Workflows , a feature now in public preview that GitHub launched in February. Instead of writing automation scripts, you write instructions to an AI agent in plain English in a Markdown file. The agent reads issues and pull requests, runs tools, and replies on its own. It can be powered by GitHub Copilot, Anthropic's Claude, Google Gemini, or OpenAI Codex. Workflows are read-only by default, but an organization can hand one a token with...

A group of AI safety researchers says a fleet of autonomous agents that identified themselves as OpenAI systems left about 18,000 posts on a dormant 25-year-old German wiki between May and July 2026, using the site as a shared board to pool answers to a timed web task and pass around a way out of their sandbox. The activity was concentrated on DSEwiki , a German software developer wiki that runs on the ProWiki farm at wikiservice[.]at and had been edited about 20 times over the previous decade. The researchers, led by Sydney Von Arx of the AI safety nonprofit  Nightingale Collective , reconstructed the deleted pages from edit history and published their analysis along with a downloadable copy of the data. The wikis let anyone change a page with an ordinary web request, the kind normally used only to read a page rather than to write one. Agents that were restricted to reading the internet could therefore still write to the site, because the restriction was written a...

Multiple software supply chain attacks have hit the npm ecosystem, with threat actors using both malicious and poisoned versions of over 50 legitimate packages to distribute a Rust-based information stealer and a self-spreading worm, respectively. According to JFrog , the information stealer "scrapes every secret it can find on a developer's machine, hides behind an eBPF kernel rootkit, and answers to its operator over Tor." The stealer also uses the stolen credentials as a propagation mechanism, drawing similarities to the infamous Shai-Hulud worm. The new malware has been codenamed IronWorm by the software supply chain security company. By publishing itself to the npm registry in the form of trojanized packages, the approach results in a self-replicating attack. The malicious activity has been traced back to a compromised npm account named " asteroiddao ," which has been found to publish package versions containing the Rust ELF binary that's exec...

A GitHub issue opened by an account with no repository privileges was enough to execute code on the CI runners behind Anthropic's and Google's own coding-agent repositories. On OpenAI's, it was enough to hijack the next agent run. Novee Security ran the attack against each vendor's agent in the configuration that the vendor ships by default, and presented the work at Black Hat USA on August 5. Two CVEs came out of it. Both are patched. Gemini CLI carries the worst of the two. CVE-2026-12537 (CVSS 4 score: 10.0) is an OS command injection in the container launcher, reached through a crafted .gemini/.env file, which lets an unprivileged attacker run code on the host of a headless CI platform before the sandbox starts. It is fixed in Gemini CLI 0.39.1 and run-gemini-cli 0.1.22. In Claude Code, CVE-2026-54316 turned Hugging Face's public download counter into an exfiltration channel that leaked an API key one character at a time, and is fixed in 2.1.163. Every ...

OpenAI has disclosed that two of its employee devices in its corporate environment were impacted via the Mini Shai-Hulud supply chain attack on TanStack, but noted that no user data, production systems, or intellectual property were compromised or modified in an unauthorized manner. "Upon identification of the malicious activity, we worked quickly to investigate, contain, and take steps to protect our systems," OpenAI said . "We observed activity consistent with the malware's publicly described behavior, including unauthorized access and credential-focused exfiltration activity, in a limited subset of internal source code repositories to which the two impacted employees had access." The artificial intelligence (AI) upstart said only limited credential material was successfully transferred from these code repositories, adding no other information or code was impacted. Upon being alerted of the activity, OpenAI said it isolated impacted systems and identities...

Microsoft has revealed that it's pursuing legal action against a "foreign-based threat–actor group" for operating a hacking-as-a-service infrastructure to intentionally get around the safety controls of its generative artificial intelligence (AI) services and produce offensive and harmful content. The tech giant's Digital Crimes Unit (DCU) said it has observed the threat actors "develop sophisticated software that exploited exposed customer credentials scraped from public websites," and "sought to identify and unlawfully access accounts with certain generative AI services and purposely alter the capabilities of those services." The adversaries then used these services, such as Azure OpenAI Service, and monetized the access by selling them to other malicious actors, providing them with detailed instructions as to how to use these custom tools to generate harmful content. Microsoft said it discovered the activity in July 2024. The Windows maker...

Cybersecurity researchers have disclosed details of a new automated campaign called Megalodon that has pushed 5,718 malicious commits to 5,561 GitHub repositories within a six-hour window. "Using throwaway accounts and forged author identities (build-bot, auto-ci, ci-bot, pipeline-bot), the attacker injected GitHub Actions workflows containing base64-encoded bash payloads that exfiltrate CI secrets, cloud credentials, SSH keys, OIDC tokens, and source code secrets to a C2 server at 216.126.225[.]129:8443," SafeDep said in a report. The complete list of data harvested by the malware is below - CI environment variables, /proc/*/environ, and PID 1 environment Amazon Web Services (AWS) credentials Google Cloud access tokens Instance role credentials obtained by querying AWS IMDSv2, Google Cloud metadata, and Microsoft Azure Instance Metadata Service (IMDS) endpoints SSH private keys Docker and Kubernetes configurations Vault tokens Terraform crede...

The Miasma supply chain campaign has sparked a fresh attack wave called Hades , this time involving 37 malicious wheel artifacts across 19 packages in the Python Package Index (PyPI) registry, as the Mini Shai-Hulud-style attacks continue to be refined and splintered to target specific ecosystems. "The compromised releases shipped a *-setup.pth file that attempts to execute automatically during Python startup, download the Bun JavaScript runtime, and run an obfuscated JavaScript payload named _index.js," Socket said in a new analysis. The list of identified packages is below - bramin 0.0.2, 0.0.3, 0.0.4 cmd2func 0.2.2, 0.2.3 coolbox 0.4.1, 0.4.2 dynamo-release 1.5.4 executor-engine 0.3.4, 0.3.5 executor-http 0.1.3, 0.1.4 funcdesc 0.2.2, 0.2.3 magique 0.6.8, 0.6.9 magique-ai 0.4.4, 0.4.5 mrbios 0.1.1, 0.1.2 napari-ufish 0.0.2, 0.0.3 nucbox 0.1.2, 0.1.3 okite 0.0.7, 0.0.8 pantheon-agents 0.6.1, 0.6.2 pantheon-toolsets 0.5....

OpenAI revealed a GitHub Actions workflow used to sign its macOS apps led to the download of the malicious Axios library on March 31, but noted that no user data or internal system was compromised. "Out of an abundance of caution, we are taking steps to protect the process that certifies our macOS applications are legitimate OpenAI apps," OpenAI said in a post last week. "We found no evidence that OpenAI user data was accessed, that our systems or intellectual property were compromised, or that our software was altered." The disclosure comes a little over a week after Google Threat Intelligence Group (GTIG) attributed the supply chain compromise of the popular npm package to a North Korean hacking group it tracks as UNC1069 . The attack enabled the threat actors to hijack the package maintainer's npm account to push two poisoned versions 1.14.1 and 0.30.4 that came embedded with a malicious dependency named "plain-crypto-js," which depl...

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...

Grafana Labs, on May 19, 2026, said an investigation into its recent breach found no evidence of customer production systems or operations being compromised. It said the scope of the incident is limited to the Grafana Labs GitHub environment, which includes public and private source code along with internal GitHub repositories. "After the initial assessment, we found that in addition to source code, the downloaded content included GitHub repositories that some Grafana Labs teams use to collaborate on and store internal operational information and other details about our business," it said . "This includes business contact names and email addresses that would be exchanged in a professional relationship context, not information pulled from or processed through the use of production systems or the Grafana Cloud platform." The open-source visualization software maker also noted that the breach originated from the TanStack npm supply chain attack orchestrated ...

GitHub on Tuesday launched a technical preview of a new AI-powered  pair programming  tool that aims to help software developers write better code across a variety of programming languages, including Python, JavaScript, TypeScript, Ruby, and Go. Copilot , as the code synthesizer is called, has been developed in collaboration with  OpenAI , and leverages Codex, a new AI system that's trained on publicly available source code and natural language with the goal of translating comments and code written by a user into auto-generated code snippets. "GitHub Copilot draws context from the code you're working on, suggesting whole lines or entire functions," GitHub CEO Nat Friedman  said  in a blog post. "It helps you quickly discover alternative ways to solve problems, write tests, and explore new APIs without having to tediously tailor a search for answers on the internet." Despite its function as an AI-based autocomplete for writing boilerplate code, the Micr...

OpenAI on Wednesday disclosed six new instances of "unexpected or concerning model behavior" that took place over the past six months, while sharing a new framework for reporting, tracking, investigating, and disclosing model misalignment in a bid to improve transparency. "As AI systems grow more advanced and more widely deployed, we need to build a broader and better-informed consensus on the progress of alignment research," OpenAI said. "We do not believe that the AI industry has solved alignment and monitoring to a sufficient degree to continue responsibly scaling at maximum speed for much longer." "Decisions about how AI development should proceed in the months and years to come need to draw on evidence that people outside the companies building frontier models can examine for themselves." The six incidents are outside of the recently disclosed misaligned activity targeting Hugging Face , DseWiki , and RubyGems . Details of the inc...