Tag
OpenAI shares a product demo walkthrough of PR scans, showing how scan results are reviewed directly within a pull request workflow.
Agentic CleanSlop launches on Product Hunt, letting developers authenticate, scan and fix vibe-coded TypeScript/Node.js apps directly from coding agents like Claude Code, Codex, and Cursor, surfacing real-world risks instead of hundreds of findings.
GitHub 宣布 Agentic Autofix 正式 GA,面向 Enterprise Cloud 的 Code Security 与 Advanced Security 客户:将代码扫描告警指派给 Copilot 后,它会探索相关文件、提出修复建议、重新运行 CodeQL 并开启草稿 PR 供人工审查。该功能仍是审查工作流而非自动合并,消耗 AI Credits 和 Actions 分钟数。
GitHub Security Lab开源了gh-secure工具,一条命令即可为公开仓库开启分支保护、密钥扫描、Dependabot、代码扫描等五项安全防护,并支持在Copilot应用与Copilot CLI中使用。
Codex Security Cloud receives a major upgrade with default access to cyber-capable models through Daybreak Blue, offering continuous GitHub repo scanning, commit review, and automated fix preparation as a plugin.
Devin introduces Code Scans, an AI-powered tool that investigates codebases based on user-defined goals, identifies improvements, and automatically generates pull requests to implement changes, aiming to reduce engineering overhead.
VibeDefend by CybeDefend is a security tool that installs with one command on AI coding agents, enforcing business and security rules by scanning code diffs in real-time.
OpenAI open-sourced Codex Security, a CLI and TypeScript SDK for scanning code for security vulnerabilities, using AI to assist in finding and validating issues.
Reintroducing the Codex Security plugin, an open-source tool that can analyze codebases for security threats, generate fixes, and export results to various platforms.
Vercel Labs releases deepsec, an open-source agent-powered vulnerability scanner that uses top-tier AI models to perform on-demand review of large codebases and surface hard-to-find vulnerabilities.
Cloudflare explains how to build a model-agnostic vulnerability scanning harness that treats AI models as interchangeable components, enabling cross-repo tracing and false positive reduction at scale.
Codex Security has scanned 30,000 code repositories, over 30 million commits, and fixed over 500,000 vulnerabilities in three months, demonstrating the efficiency of AI automation.
ArgusRed is a CLI tool that uses a post-trained AI model to perform security scanning and penetration testing on codebases, outputting detailed markdown reports. It offers two modes: security scan (read-only) and pen test (active exploits) with optional exploit verification.
Anthropic has launched Claude Security into public beta for Enterprise customers, an AI-driven tool that scans codebases to identify vulnerabilities and propose patches by understanding business logic and data flows.
The Government of Alberta used Claude Code to scan 466 million lines of code in 20 hours, identifying and fixing cybersecurity vulnerabilities across its systems, a task that would have taken years using traditional methods.