nginx and Java patch AI-found remote code execution bugs, and Google's Gemini 4 Neon lands between Sonnet and Opus on price
nginx 1.30.7 and 1.31.9 fix two HTTP/2 bugs that Wiz says allow unauthenticated code execution, Calif's Java4Shell hits OpenJDK on AVX-512 servers, Gemini 4 Neon arrives at $3/$15 per million tokens, and OpenAI explains the permission profiles that limit what Codex can touch.
nginx 1.30.7 and 1.31.9 fix two HTTP/2 bugs that Wiz says allow unauthenticated code execution, Calif's Java4Shell hits OpenJDK on AVX-512 servers, Gemini 4 Neon arrives at $3/$15 per million tokens, and OpenAI explains the permission profiles that limit what Codex can touch.
Gemini 4 Neon vs Claude Opus 5.5 and Sonnet 5.5: price, per-task cost and when to switch
Google released Gemini 4 Neon on November 18 at $3 input and $15 output per million tokens, priced between Claude Sonnet 5.5 and Opus 5.5. On Artificial Analysis it scores 61 at xhigh for $6.44 per task. Here is how it compares, and why the answer changes on December 1.
nginx 1.30.7 and 1.31.9 fix two HTTP/2 remote code execution bugs found with AI: what to patch first
nginx 1.30.7 and 1.31.9 fix ten CVEs, including two HTTP/2 bugs that Wiz says allow unauthenticated remote code execution: CVE-2026-123007 (since 1.9.5) and CVE-2026-123633 (since 1.19.7). How to check your servers, the workaround, and why AI keeps finding these bugs.
Java4Shell: how to check if your JVM is affected by the OpenJDK Base64 bug Codex found
Java4Shell, disclosed by Calif on November 17, 2026, is a HotSpot Base64 bug that can lead to remote code execution on OpenJDK 17.0.6+ running on x86-64 CPUs with AVX-512 VBMI. Check your JDK, CPU and JVM flags, and see how Codex found it.
Codex sandbox permission profiles: config.toml rules for secrets, domains and MCP servers
OpenAI's Inside the Codex sandbox post shows how permission profiles in config.toml control what Codex commands can read, write and reach. Copyable profiles for hiding secrets, allowlisting domains and sandboxing MCP servers, plus the gaps OpenAI admits.
article2media turns one article or video into Xiaohongshu cards, long images, WeChat layouts and narrated video
article2media is a free, open-source set of Claude Code and Codex skills that turns one article or video into publish-ready Chinese visual content for Xiaohongshu, WeChat and short video.
cook: an agent skill that iterates visual builds until they match the references
cook is an agent skill for visual builds that have to match reference images or videos. It gives the agent a target, a numeric bar and time, then loops through build, compare, critique and fix.
cracked: agent skills for company-wise mock interviews, OAs and resume roasts
cracked is a pack of 19 agent skills that turn Claude Code, Codex, Cursor, GitHub Copilot or Gemini CLI into an interviewer, coach and career team for tech placements.
Reason Network: your team's coding agents, talking to each other
Reason Network is a free, open-source engine that connects coding agent sessions across a team's computers so they can see each other and exchange messages.
rossark-motion-skill: animate drawn illustrations with a Claude Code skill
rossark-motion-skill is a Claude Code skill for animating drawn illustrations in React Native and SwiftUI, with a small motion engine, live-face templates, and tools that measure reference video frame by frame.
Appwrite: An Open-Source Backend for Apps and AI Agents
Appwrite is an open-source, MCP and agent-first platform for building and scaling apps, with Auth, Databases, Storage, Functions, Sites, Messaging, Realtime, and a firewall in one place.