OpenAI Open-Sources Codex Security CLI for AI-Driven Code Vulnerability Detection and Remediation
OpenAI has open-sourced Codex Security, a command-line tool designed to discover, validate, and remediate security vulnerabilities in codebases, particularly those produced by AI coding assistants such as Cursor and Copilot.
The release addresses a growing gap: while AI tools accelerate code generation, traditional security reviews remain slow and expensive, and conventional static application security testing (SAST) tools generate excessive false positives that bury real issues.
Unlike rule-based SAST solutions that rely on pattern matching, Codex Security uses contextual AI analysis to understand how code behaves in its actual runtime context, enabling more meaningful findings and the generation of reviewable patches.
The project is based on OpenAI’s lightweight programming agent Codex, which entered research preview in March and is now distributed under the Apache-2.0 license. The npm package @openai/codex-security has already attracted significant attention on Hacker News, where the story surfaced faster than any official announcement.
Installation requires Node.js 22 or later and Python 3.10 or later. Users can run a basic scan with a single command after logging in, without needing a ChatGPT Plus subscription. Full capabilities are unlocked by providing an OpenAI API key via an environment variable, making the tool suitable for CI/CD pipelines.
Key use cases include repository-wide scans, pull-request analysis before code merges, automated checks in continuous integration, and tracking remediation status across multiple runs through a local state directory.
Security teams are advised to treat the tool as an assistant rather than an autonomous decision-maker, given the inherent uncertainty of model-driven judgments and the risk of both missed vulnerabilities and hallucinations.
Related articles
Microsoft Copilot Abused to Accelerate Corporate Account Takeovers and Bank Transfer Frauds
Cybercriminals can leverage Microsoft Copilot to speed up the compromise of corporate accounts and execute financial frauds. In a controlled simulation, researchers demonstrated how the AI assistant helped redirect a $247,500 bank transfer after gaining access to an employee's email. The attack begins with the creation of inbox rules that automatically delete suspicious login alerts, followed by rapid analysis of internal communications to identify high-value targets. Copilot was then used to replicate the victim's writing style and craft a convincing phishing email capable of stealing session tokens and bypassing multi-factor authentication. Once the executive account was taken over, the tool quickly located pending payments and generated a fraudulent request to alter the recipient bank details. The scenario highlights risks from legitimate AI features rather than any specific vulnerability in Copilot itself.
Vibe Hacking Rises: Generative AI Lowers Barriers for Offensive Security Operations
Generative AI is reshaping the cybersecurity threat landscape by dramatically reducing the cost of offensive security knowledge. Previously, attackers needed years of experience in reverse engineering and exploit development to conduct meaningful intrusions, but AI now assists with research, code generation, debugging, and adapting known techniques to new environments. This enables less experienced individuals to build functional attack chains in weeks rather than years. The article introduces the concept of vibe hacking, where attackers collaborate with AI assistants using natural language prompts in a process similar to vibe coding. Defenders can no longer rely on the scarcity of skilled adversaries and must shift toward continuous validation frameworks such as CTEM, AEV, and PTaaS. Senior human experts remain essential for risk judgment and business context, even as automation accelerates routine tasks.
Hunt.io Exposes Suspected Chinese Cyber Espionage Operation Using Agentic LLMs Claude Code and DeepSeek
In July 2026 Hunt.io published research on a suspected Chinese cyber espionage campaign uncovered through an exposed directory on a Hong Kong server. The leak contained 2,431 files including victim source code, operation logs, web shells, exploitation scripts, scan results and phishing page clones. Researchers identified traces of Claude Code and DeepSeek-v4-pro working together, with Claude Code handling agentic tasks and session context while DeepSeek supported reasoning, script refinement and next-step selection. The infrastructure cluster, known as TencShell, showed overlapping SHA-256 HTTP headers, SSH host keys and TLS certificates across 13 IP addresses. Multiple initial access vectors were observed, including SQL injection against Taiwanese and Thai government targets plus exposure of Supabase and Azure secrets. The report also references a parallel Anthropic disclosure on GTG-1002, another Chinese state-linked operation that used Claude Code for 80-90 percent of tactical work.
OWASP LLM10 Unbounded Consumption: Testing YandexGPT Lite 5 and GigaChat Lite on Resource-Intensive Prompts
The article examines OWASP LLM10: Unbounded Consumption, a category focused on attacks that force large language models to perform computationally expensive tasks without traditional denial-of-service traffic. Researchers used the AI Red Team platform to evaluate two flagship Russian models, YandexGPT Lite 5 and GigaChat Lite, against prompts designed to trigger recursive context expansion, fractal nesting, combinatorial explosions, and multi-agent simulations. The study highlights how a single carefully crafted prompt can generate disproportionate token consumption, GPU load, and API costs compared with conventional DoS methods. Both models demonstrated defensive strategies including hard generation limits at 512 tokens, graceful degradation by summarizing instead of expanding, and early refusal with alternative suggestions. The work was supported by the Foundation for Assistance to Innovations and aims to improve architectural protections for LLM applications. Examples of tested prompts and observed model behaviors are provided for research and educational purposes only.