threat-intel GitHub Copilot Refuses Harmful Requests in Chat, Then Writes Them in Code Researchers at GitHub discovered a method to bypass the safety mechanisms of AI coding assistant GitHub Copilot. By framing requests for harmful content as part of a seemingly legitimate coding task – specifically, build… The Hacker News · Jul 8, 2026 High ai safetyjailbreakcode generation
threat-intel Critical Vulnerability Exposes GitHub Agentic Workflows to Prompt Injection A critical vulnerability, dubbed GitLost, has been identified in GitHub Agentic Workflows, allowing unauthenticated attackers to potentially leak private repository data by injecting prompts into public GitHub Issues. Th… SecurityWeek · Jul 8, 2026 Critical prompt injectionai securityagentic ai
threat-intel 'GitLost' Flaw Leaks Private Data from GitHub's Agentic Workflows A critical prompt injection vulnerability, dubbed ‘GitLost,’ has been discovered in GitHub’s Agentic Workflows, allowing unauthenticated attackers to steal private data from an organization’s repositories by crafting a G… Dark Reading · Jul 7, 2026 High prompt injectionagentic aisecurity vulnerability
threat-intel Public GitHub Issue Could Trick GitHub Agentic Workflows Into Leaking Private Repo Data Researchers at Noma Security discovered a vulnerability, dubbed ‘GitLost,’ in GitHub Agentic Workflows that allows attackers to trick AI agents into leaking private repository content simply by posting a malicious issue… The Hacker News · Jul 7, 2026 High prompt injectionai agentgithub
threat-intel ⚡ Weekly Recap: Proxy Botnets, Browser Ransomware, AI Agent Tricks, Fake PoC Malware and More This week’s security recap highlighted several concerning trends, including a disruption of the NetNut residential proxy network used for botnet operations, a fake Proof-of-Concept (PoC) malware targeting vulnerability r… The Hacker News · Jul 6, 2026 High CVE-2026-48276CVE-2026-48283CVE-2026-48277USESSPbotnetproxymalware
threat-intel SkillCloak Lets Malicious AI Agent Skills Evade Static Scanners with Self-Extracting Packing Researchers at the Hong Kong University of Science and Technology have developed a method to bypass AI coding agent scanners by using self-extracting packing and character substitution to disguise malicious skills. Their… The Hacker News · Jul 6, 2026 High aiskillsmalware
threat-intel North Korean Hackers Publish 108 Malicious Packages and Extensions in PolinRider Campaign North Korean threat actors, linked to the Contagious Interview campaign, have been publishing 108 malicious packages and extensions across platforms like npm, Packagist, and Go, as part of the PolinRider operation. This… The Hacker News · Jul 4, 2026 High KPnorth koreangithubmalware
threat-intel Armored Likho digging a snake pit: inside the covert BusySnake Stealer campaign The Securelist report details a new cyber espionage campaign conducted by the Armored Likho (Eagle Werewolf) APT group, targeting government agencies and the electric power sector globally. The group utilizes a sophistic… Securelist · Jul 3, 2026 High RUBRKZaptphishinginfostealer
malware New ChocoPoC RAT Targets Vulnerability Researchers via Fake PoC Exploit Repos A new remote access trojan (RAT) called ChocoPoC is targeting vulnerability researchers through deceptive proof-of-concept (PoC) repositories on GitHub. The malware, disguised within Python dependencies, steals sensitive… The Hacker News · Jul 2, 2026 High CVE-2025-64446CVE-2025-55182CVE-2025-14847KRproof-of-conceptremote access trojangithub
threat-intel Attackers Exploit SimpleHelp CVE-2026-48558 to Deploy TaskWeaver and Djinn Stealer An attacker exploited a critical vulnerability (CVE-2026-48558) in SimpleHelp’s OpenID Connect (OIDC) flow to deploy the TaskWeaver and Djinn Stealer malware. This allowed for unauthorized access to authenticated ‘Techni… The Hacker News · Jun 30, 2026 Critical CVE-2026-48558USoidccredential theftai
threat-intel Hijacked npm and Go Packages Use VS Code Tasks to Deploy Python Infostealer A sophisticated cyberattack has been uncovered involving hijacked npm and Go packages designed to deploy a Python-based information stealer. Attackers leveraged a VS Code task trigger to execute malicious code disguised… The Hacker News · Jun 29, 2026 High KPvscodenpmfont-file
supply-chain Miasma Malware Targets npm Packages and GitHub Actions in Supply Chain Attack A sophisticated supply chain attack, spearheaded by the Miasma malware family (linked to Mini Shai-Hulud and Hades), is targeting npm packages and GitHub Actions workflows. The attackers are leveraging compromised npm pa… The Hacker News · Jun 26, 2026 High RUsupply chainnpmgithub actions
supply-chain Cordyceps CI/CD Flaws Expose 300+ GitHub Repositories to Supply-Chain Attacks A new vulnerability, dubbed 'Cordyceps,' has been discovered in CI/CD workflows, allowing unauthorized access and control over hundreds of GitHub repositories across major tech companies. The flaw stems from overly permi… The Hacker News · Jun 24, 2026 Critical cicdsupply chaingithub
supply-chain Exploitable CI/CD Vulnerabilities Expose Millions of Repositories to Hijacking A new vulnerability, dubbed ‘Cordyceps,’ has been identified within CI/CD workflows across numerous open-source projects, allowing unauthorized access and control over developer repositories. The flaws, primarily found i… SecurityWeek · Jun 24, 2026 High ci/cdsupply chaingithub actions
supply-chain GitHub Updates actions/checkout to Block Common Pwn Request Attack Patterns GitHub is implementing a security update to its "actions/checkout" action to mitigate a common supply chain attack vector. The update, effective June 18, 2026, will block the execution of malicious code from untrusted fo… The Hacker News · Jun 23, 2026 High supply-chaingithubactions
threat-intel Crypto Heist Fueled by Elaborate Fake Reputation-Boosting Campaign A sophisticated cybercrime campaign, orchestrated by unknown threat actors, is utilizing a multi-channel approach to distribute a cross-platform clipboard hijacker designed to steal cryptocurrency. The campaign leverages… Dark Reading · Jun 22, 2026 High USclipboard hijackingreputation manipulationcrypto theft
threat-intel Every AI Agent Is an Identity. Most Organizations Don't Treat Them That Way This article highlights a growing security risk within organizations due to the widespread adoption of AI agents. Traditional identity security models, built around controlling employee and service accounts, are being by… BleepingComputer · Jun 19, 2026 High aiartificial intelligenceidentity management
threat-intel Novo Nordisk Breach Exposes Software Development Pipeline Risk A breach at Novo Nordisk, facilitated by a leaked GitHub token, exposed a significant amount of sensitive data, including patient clinical trial information, healthcare professional records, and proprietary drug developm… Dark Reading · Jun 18, 2026 High DKgithubsecretssupply-chain
threat-intel Crypto Clipper Campaign Abuses Fake Reviews, AI Narrators, and VirusTotal Comments A threat actor is employing deceptive tactics to promote a cryptocurrency clipboard hijacker, leveraging fake reviews, AI-generated content, and manipulated reputation systems across multiple online platforms. The campai… The Hacker News · Jun 17, 2026 High USfake reviewsreputation managementai
supply-chain GitHub dismissed security reports on flaws now exploited by supply-chain worm, researchers say A supply-chain worm, dubbed Shai-Hulud, is exploiting design flaws in GitHub to infect hundreds of software packages and developer accounts worldwide. The vulnerabilities, initially flagged by Deep Specter Research, were… The Record · Jun 16, 2026 High GBFRsupply chainvulnerabilitygithub
