Tag
Neal Bridges released VulnHunter, an open-source fork of Capital One's agentic AI vulnerability-hunting and PoC-development kit, updated to run on any agent harness with sandboxed containerized exploit validation and measured-impact PoCs.
OpenAI announced new capabilities for Codex, including reusable cloud environments that work across devices, along with updates to the CLI, code review experience, security tools, and API enhancements at their Dev Day event.
The article compares AI-powered security tools that detect real code vulnerabilities beyond basic linting, with mentions of tools like Snyk, Semgrep, and Coderabbit.
An open-source cybersecurity skills library for AI agents with over 800 skills across 34 security domains, designed for authorized penetration testing and security research.
The article introduces 'gh secure', a GitHub CLI extension that enables free security settings in public repositories with a single command, following best practices from the GitHub Security Lab.
Vex8s is an experimental tool that generates VEX documents by analyzing Kubernetes security contexts and vulnerability data with an embedded ML model to determine which CVEs are actually exploitable in a cluster.
A user reports encountering the Anubis bot protection screen with every click on Lobsters, suggesting a recent change that disrupts user experience.
The article discusses the challenge of creating a policy layer for AI agents, balancing security with usability, where human-in-the-loop approvals may slow decisions but stricter guardrails can hinder usability.
An autonomous AI red teaming system named PentAGI uses three agents to scan, exploit, and report vulnerabilities, making serious security testing more accessible while stressing authorized use only.
Awesome OSINT Arsenal provides a one-command installation for over 750 open-source intelligence tools across 50 security categories, supporting multiple Linux distributions and Android via Termux.
The author presents a secure method for giving coding agents SSH access to real servers using an intermediary client that holds keys and signs commands, with per-host policies, live monitoring, and audit logs, while discussing limitations and seeking feedback.
Google points out that relying solely on large language models in vulnerability mining is not enough; the key is to combine an agent-based vulnerability discovery framework. For example, its team used this tool to discover multiple critical vulnerabilities in a short time.
Introduces the Awesome OSINT Arsenal project on GitHub, systematically organizing 753+ OSINT and security tools, covering 50 categories, with one-click installation scripts and Termux support.
A GitHub user named A-poc has compiled over 150 commonly used red team tools, categorized by phase from information gathering to cleanup, along with 19 practical tips for security professionals to learn and research.
This project is an AI skill routing package for reverse engineering and penetration testing. Through routing.md, it enables AI to automatically select the appropriate tools and methods, lowering the barriers to security offense and defense.
Arc Gate is an AI security tool that focuses on inspecting entire sessions rather than individual messages, offering a distinct approach to security monitoring.
Introducing Claude-BugHunter, a skill pack designed for Claude Code, containing 71 skills, 15 slash commands, and 681 public report patterns, aiming to transform Claude Code into an advanced bug bounty hunter or red team operator.
An open detection rule format for AI agent security threats, inspired by Sigma/YARA, aims to standardize detection of prompt injection, tool abuse, and other agent attacks, though it notes limitations against semantic attacks.
Anthropic 今日宣布启动「Anthropic Cyber Mission」长期计划，推出关键基础设施防御计划（CIDP）与面向开源项目的免费 OSS Scanner 漏洞扫描服务，并将 Project Glasswing 整合进扩展后的 Cyber Verification Program。