---
schema_version: "newruntime-topic-hub-v0.2"
type: "topic_hub"
stable_id: "topic_hub:security"
slug: "security"
title: "Security - New Runtime"
description: "A New Runtime topic hub collecting signals, patterns, field notes, and public sources about security."
retrieval_nugget: "A New Runtime topic hub collecting signals, patterns, field notes, and public sources about security. Security is tracked here as an evidence-linked topic, not as a static glossary entry. The page connects raw observations to pattern hypotheses, longer analysis, and public sources. Use it as the canonical landing page before drilling into individual records."
answer: ["Security is tracked here as an evidence-linked topic, not as a static glossary entry.","The page connects raw observations to pattern hypotheses, longer analysis, and public sources.","Use it as the canonical landing page before drilling into individual records."]
search_intents: ["security","security AI agents","security software"]
status: "featured"
last_updated: "2026-08-01"
record_date: "2026-08-01"
date_kind: "last_updated"
counts: {"total":36,"signals":25,"patterns":0,"posts":10,"atlas":1,"sources":65}
routes: {"html":"https://newruntime.com/topics/security/","markdown":"https://newruntime.com/topics/security.md","json":"https://newruntime.com/topics/security.json"}
source_urls: ["https://aitmpl.com/component/hook/dangerous-command-blocker","https://anthropic.com/engineering/claude-code-auto-mode","https://blog.cloudflare.com/open-sourcing-our-privacy-proxy-cli/?utm_campaign=cf_blog&utm_content=20260727&utm_medium=organic_social&utm_source=twitter","https://blog.cloudflare.com/temporary-accounts","https://blog.google/innovation-and-ai/products/gemini-app/gemini-spark-updates-july-2026/","https://blog.lukaszolejnik.com/supply-chain-risk-of-agentic-ai-infecting-infrastructures-via-skill-worms","https://blog.palantir.com/securing-agents-in-production-agentic-runtime-1-5191a0715240","https://blogs.nvidia.com/blog/open-secure-ai-alliance/","https://blogs.nvidia.com/blog/open-secure-ai-alliance/?nvid=nv-csfg-990052","https://claude.com/product/claude-security","https://cloudflare.registration.goldcast.io/webinar/7e56b64f-42cc-4e05-a304-899981ba10e6?utm_medium=organic-social&utm_source=twitter&utm_campaign=2026-q3-acq-apac_en-modernsec-ge-wb-general-bfsi_vertical_wbn-jul&utm_content=post1","https://deepmind.google/blog/introducing-gemini-3-5-flash-cyber/?utm_source=x&utm_medium=social&utm_campaign=&utm_content="]
top_sources: ["https://aitmpl.com/component/hook/dangerous-command-blocker","https://anthropic.com/engineering/claude-code-auto-mode","https://blog.cloudflare.com/open-sourcing-our-privacy-proxy-cli/?utm_campaign=cf_blog&utm_content=20260727&utm_medium=organic_social&utm_source=twitter","https://blog.cloudflare.com/temporary-accounts","https://blog.google/innovation-and-ai/products/gemini-app/gemini-spark-updates-july-2026/","https://blog.lukaszolejnik.com/supply-chain-risk-of-agentic-ai-infecting-infrastructures-via-skill-worms","https://blog.palantir.com/securing-agents-in-production-agentic-runtime-1-5191a0715240","https://blogs.nvidia.com/blog/open-secure-ai-alliance/","https://blogs.nvidia.com/blog/open-secure-ai-alliance/?nvid=nv-csfg-990052","https://claude.com/product/claude-security","https://cloudflare.registration.goldcast.io/webinar/7e56b64f-42cc-4e05-a304-899981ba10e6?utm_medium=organic-social&utm_source=twitter&utm_campaign=2026-q3-acq-apac_en-modernsec-ge-wb-general-bfsi_vertical_wbn-jul&utm_content=post1","https://deepmind.google/blog/introducing-gemini-3-5-flash-cyber/?utm_source=x&utm_medium=social&utm_campaign=&utm_content="]
---

# Security - New Runtime

A New Runtime topic hub collecting signals, patterns, field notes, and public sources about security.

## Retrieval answer

A New Runtime topic hub collecting signals, patterns, field notes, and public sources about security. Security is tracked here as an evidence-linked topic, not as a static glossary entry. The page connects raw observations to pattern hypotheses, longer analysis, and public sources. Use it as the canonical landing page before drilling into individual records.

## Patterns


## Field Notes

- [Stateless MCP Makes Small, Auditable Agent Tools Practical Again](https://newruntime.com/posts/simon-stateless-mcp-practitioner-reset/): Simon Willison's mcp-explorer, datasette-mcp, and llm-mcp-client show how the stateless specification lowers implementation cost and narrows agent capabilities.
- [Gemini Spark Moves Browser Agents Into Chrome Sessions](https://newruntime.com/posts/gemini-spark-chrome-auto-browse/): Gemini Spark now integrates with Chrome auto browse, using logged-in browser context with permission while keeping users in the loop for sensitive actions.
- [LangSmith LLM Gateway Puts Runtime Controls Between Agents and Models](https://newruntime.com/posts/langsmith-llm-gateway-runtime-controls/): LangSmith LLM Gateway turns spend caps, rate limits, fallbacks, redaction, and provider routing into one governed layer for production agents.
- [Vercel Passport Makes Identity a Deployment Boundary](https://newruntime.com/posts/vercel-passport-agent-identity-boundary/): Vercel Passport is now generally available, adding verified identity tokens, group claims, audit events, and automation bypasses to protected deployments.
- [Vercel Sandbox Adds Unix Boundaries for Multi-Agent Work](https://newruntime.com/posts/vercel-sandbox-multi-user-agents/): Vercel Sandbox now supports multiple Linux users and groups, giving each agent a private home directory plus an explicit shared workspace.
- [Claude Mythos Moves Cryptanalysis Into the Verification Bottleneck](https://newruntime.com/posts/anthropic-claude-cryptographic-weaknesses/): Anthropic's cryptography research shows a frontier model finding HAWK and reduced-round AES attacks quickly, while human validation and disclosure become the scarce production step.
- [Codex Security CLI Turns Security Review Into a Scannable Workbench](https://newruntime.com/posts/codex-security-cli-scan-workbench/): OpenAI's Codex Security CLI packages repository, diff, working-tree, export, validation, and patch flows into a security-review workbench rather than a single scanner command.
- [DeepsecBench Makes Security Agents a Cost/Recall Tradeoff](https://newruntime.com/posts/deepsecbench-security-agent-economics/): Vercel's DeepsecBench reframes security-agent evaluation around recall, precision, cost, total scan time, and a hidden benchmark that resists training leakage.
- [Cloudflare pvcli Makes Privacy Protocols Debuggable Like Infrastructure](https://newruntime.com/posts/cloudflare-pvcli-privacy-debugger/): Cloudflare open-sourced pvcli, a curl-like debugger for OHTTP-style privacy flows where no one party is supposed to see the whole request path.
- [Capital One's VulnHunter Points AI at Real Attack Paths](https://newruntime.com/posts/capital-one-vulnhunter-attacker-first-security-agent/): Capital One's VulnHunter shows a useful shift in AI security tooling: an agent should connect a fix to a reproducible attack path, not only generate a diff.

## Recent Raw Signals

- 2026-07-31: [Cloudflare: Adversaries aren't breaking in—they’re logging in.](https://newruntime.com/signals/cloudflare-adversaries-aren-t-breaking-in-they-re-logging-in/)
- 2026-07-30: [Anthropic: In a review of our cybersecurity evaluations, we found three incidents in which a Claude model...](https://newruntime.com/signals/anthropic-in-a-review-of-our-cybersecurity-evaluations-we-found-three-incidents/)
- 2026-07-30: [Cloudflare: Final breakout block starting now at #CloudflareConnect Sydney!](https://newruntime.com/signals/cloudflare-final-breakout-block-starting-now-at-cloudflareconnect-sydney/)
- 2026-07-30: [OpenClaw: OpenClaw is maturing.](https://newruntime.com/signals/openclaw-openclaw-is-maturing/)
- 2026-07-29: [OpenAI: We quietly released the open-source Codex Security CLI, but Hacker News found it before we had...](https://newruntime.com/signals/openai-we-quietly-released-the-open-source-codex-security-cli-but-hacker-news-fo/)
- 2026-07-28: [Factory: We're firm believers in the open security ecosystem, contributing across our platform: • Publi...](https://newruntime.com/signals/factory-we-re-firm-believers-in-the-open-security-ecosystem-contributing-across/)
- 2026-07-28: [GitHub: 5.](https://newruntime.com/signals/github-5/)
- 2026-07-27: [Cloudflare pvcli Makes Privacy Protocols Debuggable Like Infrastructure](https://newruntime.com/signals/cloudflare-pvcli-privacy-debugger/)
- 2026-07-27: [Cloudflare: Fujitec migrated 3,300+ global employees from legacy VPNs to Cloudflare One (ZTNA) in just 45...](https://newruntime.com/signals/cloudflare-fujitec-migrated-3-300-global-employees-from-legacy-vpns-to-cloudflar/)
- 2026-07-27: [Open Secure AI Alliance Turns the AI-Safety Fight Into a Stack Question](https://newruntime.com/signals/open-secure-ai-alliance-open-defense-stack/)
- 2026-07-27: [OpenClaw: NVIDIA has been an incredible partner in helping make OpenClaw more secure.](https://newruntime.com/signals/openclaw-nvidia-has-been-an-incredible-partner-in-helping-make-openclaw-more-sec/)
- 2026-07-27: [Vercel Developers: Nuxt 4.5.1 and 3.21.10 fix multiple security vulnerabilities.](https://newruntime.com/signals/vercel-developers-nuxt-4-5-1-and-3-21-10-fix-multiple-security-vulnerabilities/)
- 2026-07-27: [Vercel: DeepsecBench evaluates model accuracy, cost, and speed in finding cybersecurity vulnerabilitie...](https://newruntime.com/signals/vercel-deepsecbench-evaluates-model-accuracy-cost-and-speed-in-finding-cybersecu/)
- 2026-07-24: [Claude: Opus 5 is available today on all paid plans and the Claude API, priced the same as Opus 4.8.](https://newruntime.com/signals/claude-opus-5-is-available-today-on-all-paid-plans-and-the-claude-api-priced-the/)
- 2026-07-23: [GitHub: Protect your secrets.](https://newruntime.com/signals/github-protect-your-secrets/)
- 2026-07-23: [Google DeepMind: To ensure this model is deployed responsibly, we’re starting with a limited-access pilot for g...](https://newruntime.com/signals/google-deepmind-to-ensure-this-model-is-deployed-responsibly-we-re-starting-with/)

## Public Sources

- https://aitmpl.com/component/hook/dangerous-command-blocker
- https://anthropic.com/engineering/claude-code-auto-mode
- https://blog.cloudflare.com/open-sourcing-our-privacy-proxy-cli/?utm_campaign=cf_blog&utm_content=20260727&utm_medium=organic_social&utm_source=twitter
- https://blog.cloudflare.com/temporary-accounts
- https://blog.google/innovation-and-ai/products/gemini-app/gemini-spark-updates-july-2026/
- https://blog.lukaszolejnik.com/supply-chain-risk-of-agentic-ai-infecting-infrastructures-via-skill-worms
- https://blog.palantir.com/securing-agents-in-production-agentic-runtime-1-5191a0715240
- https://blogs.nvidia.com/blog/open-secure-ai-alliance/
- https://blogs.nvidia.com/blog/open-secure-ai-alliance/?nvid=nv-csfg-990052
- https://claude.com/product/claude-security
- https://cloudflare.registration.goldcast.io/webinar/7e56b64f-42cc-4e05-a304-899981ba10e6?utm_medium=organic-social&utm_source=twitter&utm_campaign=2026-q3-acq-apac_en-modernsec-ge-wb-general-bfsi_vertical_wbn-jul&utm_content=post1
- https://deepmind.google/blog/introducing-gemini-3-5-flash-cyber/?utm_source=x&utm_medium=social&utm_campaign=&utm_content=