vulnerability Claude Code and Gemini CLI Flaws Let a GitHub Issue Reach CI Workflow Secrets Two vulnerabilities – one in Gemini CLI and another in Claude Code – have been discovered that allowed unprivileged attackers to execute code on CI runners, potentially exposing sensitive information. Gemini CLI allowed command injection, while Claude Code exploited a public download counter to leak API keys. Both have… The Hacker News · Aug 7, 2026 High CVE-2026-12537CVE-2026-54316ci/cdinput validationcommand injection
vulnerability AWS, Google, and Vercel Agent Flaws Let Attackers Trigger Tools Without Running the Model Security flaws have been discovered in agent infrastructure used by AWS, Google, and Vercel, allowing attackers to bypass model checks and directly invoke tools without a legitimate model turn. These vulnerabilities stem… The Hacker News · Aug 6, 2026 High CVE-2026-18830CVE-2026-18236CVE-2026-64650agentmodelauthorization
threat-intel Poison Claude Sells Discounted Claude Access While Its Operator Sees Every Customer Prompt Cybersecurity researchers have uncovered a network of underground services, including ‘Poison Claude,’ offering discounted access to Anthropic’s AI models (like Claude Opus) to users in China and elsewhere. These service… The Hacker News · Aug 5, 2026 High CHaisynthetic identityproxy
threat-intel Zenity Raises $125 Million in Series C Funding Zenity, an AI security company, secured $125 million in Series C funding to bolster its efforts in securing AI agentic frameworks and expanding its global presence. This investment reflects the growing need for specializ… SecurityWeek · Aug 4, 2026 Medium ISUSaisecurityagentic ai
threat-intel FOMO in the SOC: Where AI Platforms like Claude Actually Fit AI platforms like Claude are valuable tools for security teams, but they shouldn't be expected to investigate every security alert. The key is to differentiate between autonomous AI SOCs, which continuously monitor and i… The Hacker News · Aug 3, 2026 Medium aisocautonomous
threat-intel Chinese-Speaking Threat Actor Harnesses AI Models for Autonomous Cyberattacks A Chinese-speaking threat actor, operating under the aliases knaithe and KnYuan, is leveraging AI to conduct autonomous cyberattacks. Using the Hermes Agent framework and DeepSeek, they autonomously identified and exploi… Palo Alto Unit 42 · Jul 30, 2026 High CVE-2026-33017CVE-2026-21858CVE-2025-68613CNaiautonomousvulnerability
vulnerability Ruflo MCP Flaw Lets Unauthenticated Attackers Run Commands and Poison AI Memory A critical vulnerability (CVE-2026-59726) in Ruflo, an AI agent orchestration platform, allows unauthenticated remote code execution. Attackers can steal LLM API keys, harvest user conversations, and poison AI memory, le… The Hacker News · Jul 29, 2026 Critical CVE-2026-59726airemote code executionapi key theft
threat-intel Microsoft Unveils MAI-Cyber-1-Flash, Its First Cybersecurity AI Model Microsoft has released MAI-Cyber-1-Flash, its first cybersecurity AI model, designed to significantly improve vulnerability detection compared to competitors. This new model is integrated into Microsoft’s Project Percept… SecurityWeek · Jul 28, 2026 Medium aicybersecurityvulnerability detection
threat-intel Microsoft Says New Cybersecurity AI Model Helps MDASH Hit 95.95% at Half the Cost Microsoft has announced a new cybersecurity AI model, MAI-Cyber-1-Flash, integrated within its MDASH vulnerability identification and remediation harness. The model, combined with GPT-5.4, achieved a 95.95% score on Cybe… The Hacker News · Jul 28, 2026 Medium aicybersecurityvulnerability
threat-intel New Agent Data Injection Attack Can Make AI Agents Misclick or Run Attacker Commands Researchers at Seoul National University, the University of Illinois Urbana-Champaign, and Largosoft have discovered a new attack method called Agent Data Injection (ADI) that can manipulate AI agents by subtly corruptin… The Hacker News · Jul 16, 2026 High CVE-2025-32711prompt-injectiondata-exfiltrationai-security
vulnerability Cursor Flaw Lets Malicious Cloned Repositories Trigger Windows Code Execution A vulnerability in Cursor, a Git repository hosting platform for Windows, allows malicious cloned repositories to execute arbitrary code on the user's system. The flaw stems from Cursor's tendency to run a `git.exe` file… The Hacker News · Jul 15, 2026 High CVE-2026-26268CVE-2026-10591CVE-2020-26233gitwindowscode execution
threat-intel Thinking Fast and Slow in the SOC: The Case for Combining Autonomous AI with Analyst Copilots This article argues that current approaches to AI in Security Operations Centers (SOCs) are fundamentally flawed. Instead of deploying AI to handle the entire alert queue (System 2 work), security teams are often forcing… The Hacker News · Jul 13, 2026 High aisoccognitive
threat-intel Top AI Agents Built to Catch Malicious Code Can Be Tricked Into Running It Researchers at AI Now Institute have demonstrated a significant vulnerability in AI coding agents like Anthropic's Claude Code and OpenAI's Codex. By inserting a seemingly harmless binary disguised within a README file,… The Hacker News · Jul 9, 2026 High CVE-2026-39861aicode-injectionsecurity
threat-intel AI Coding Agents Found Triggering Endpoint Security Rules Built to Catch Attackers Sophos researchers discovered that AI coding assistants like Claude Code, Cursor, and OpenAI Codex are triggering traditional endpoint security rules designed to detect malicious activity. These agents, while harmless in… The Hacker News · Jul 8, 2026 Medium aicoding assistantendpoint security
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 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 Fake Bug Report Hijacks AI Coding Agents at Scale A research report by Tenet Security has revealed a critical vulnerability in AI coding agents, demonstrating how a simple, fabricated error report submitted to a bug tracking service (Sentry) can be used to hijack these… Dark Reading · Jun 30, 2026 Critical aiagentjackingerror-tracking
threat-intel Attackers Hijack Exposed AI Endpoints to Power Offensive Ops Researchers at Zenity discovered attackers are exploiting exposed AI endpoints, specifically Ollama and LiteLLM, to power offensive operations. Attackers leverage these AI agents – such as Strix and HexStrike AI – withou… Dark Reading · Jun 30, 2026 High FRaillmendpoint
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 'Djinn' Stealer Targets Cloud, AI Credentials The ‘Djinn’ stealer, delivered via a SimpleHelp vulnerability (CVE-2026-48558), is targeting cloud and AI credentials, specifically focusing on developer and administrator environments. Blackpoint Cyber’s APG tracked an… Dark Reading · Jun 29, 2026 High CVE-2026-48558DKaicredentialsstealer
