1
网信办对 Palo Alto 派拓公司在华销售产品启动网络安全审查
网信办依据国安法与网络安全法，对Palo Alto在华产品启动审查，关注关键基础设施安全。
IT之家 8 月 6 日消息，为保障关键信息基础设施安全稳定运行，防范网络安全风险隐患，维护国家安全，依据《中华人民共和国国家安全法》《中华人民共和国网络安全法》，网络安全审查办公室按照《网络安全审查办法》，对派拓公司（Palo Alto Networks）在华销售的产品实施网络安全审查。 IT之家…
2
AI Firewall – Security Gateway and Reverse Proxy for LLM Traffic
专为LLM流量打造的安全网关，集成请求分类、攻击检测与敏感信息过滤，开源且可实战部署
Article URL: https://github.com/bossandboss/Ai-Firewall Comments URL: https://news.ycombinator.com/item?id=49018165 Points: 1 # Comments: 0
3
Why Your AI Agent's Biggest Vulnerability Isn't a Missing Firewall
AI agent的最大威胁并非缺少防火墙，而是日历邀请劫持浏览器等新型攻击方式，真实案例揭示安全盲区。
(initially published at https://www.humanbound.ai/blog/why-your-ai-agents-biggest-vulnerability-isnt-a-missing-firewall ) Three incidents, one root ca…
4
Token-Flow Firewall: Semantic Runtime Auditing for Persistent AI Agents
提出Token流语义防火墙，为持久AI代理提供运行时审计，保障Agent安全。
arXiv:2607.08395v1 Announce Type: cross Abstract: Persistent AI agents extend large language models (LLMs) beyond single-turn interaction into long-li…
5
Building a Linux Security Audit Toolkit with Bash: From Firewall Checks to SSH Hardening
手把手教你用Bash打造Linux安全审计工具包，从防火墙检查到SSH加固，实操性强。
Building a Linux Security Audit Toolkit with Bash: A Practical Approach to System Hardening Linux is widely considered a secure operating system. Howe…
6
Claude Fable 5: Why Anthropic's Most Powerful AI Was Suspended?
Anthropic最强模型Claude Fable 5突遭暂停，安全与防火墙成焦点，是能力太强还是另有隐情？
Why it was suspended? can Claude Mythos and Fable 5 create what we have in imagination? I believe Security, Firewall is the issues. Because it can bre…
7
Show HN: Dex – Cost-aware analytics engineering skills for agents
让AI代理安全查数又省钱：Dex为数据栈加上成本感知与PII防火墙，语义层查询更聪明。
Hi I’m Marco, co-founder of Exmergo. Me and my team created Dex to help Analytics Engineers do real work with Claude Code (and any other coding agent)…
8
Show HN: Loopers – Open-source fail-closed firewall for AI agent runtimes
开源且支持500+模型的AI Agent防火墙，基于OWASP Top 10安全规则，内置W3C OTLP追踪与EU AI Act合规。
Article URL: https://github.com/CURSED-ME/loopers-oss Comments URL: https://news.ycombinator.com/item?id=48804865 Points: 1 # Comments: 0
9
Bitmask-Based LLM Security Firewall with reskSecure — Block Jailbreaks at Token Level
在token生成前用位掩码策略拦截越狱攻击，reskSecure实现LLM安全防火墙新思路。
Links: PyPI: https://pypi.org/project/resksecure GitHub: https://github.com/Resk-Security/reskSecure Web: https://resk.fr Most prompt injection and ja…
10
Show HN: A Firewall for AI agents with auditing
用Rust打造的AI agent防火墙，5毫秒内响应，通过计划强制执行防止幻觉和延迟问题，支持审计。
Hi all, As there are more and more agents in the internet; Security is going to be a big problem. Currently, the problem is solved using a LLM to guar…
11
Cerberus – a local firewall for AI agents' tool calls
为AI代理工具调用提供安全边界，本地防火墙开源项目Cerberus可防范恶意操控风险。
Article URL: https://github.com/Adirdabush1/cerberus Comments URL: https://news.ycombinator.com/item?id=48704458 Points: 3 # Comments: 0
12
Discussion – has anyone build a firewall for AI models yet?
围绕“AI模型防火墙”这一新赛道，探讨开源模型托管浪潮下的安全需求与创业机会。
Trying to figure out if there are already companies that have build firewall like products for AI models. Assuming everyone will now start hosting ope…
13
Show HN: Leakproof – local secret-egress firewall for Claude Code/Cursor/aider
这款开源的本地秘密出口防火墙，用本地模型智能检查敏感数据，让AI编程工具安全无忧。
Article URL: https://github.com/acunningham-ship-it/leakproof Comments URL: https://news.ycombinator.com/item?id=48576074 Points: 1 # Comments: 1
14
Packet Filtering with nftables on Linux
从iptables迁移到nftables，手把手带你掌握Linux下一代包过滤防火墙核心用法。
iptables is probably the most used firewall by all sysadmin in the Linux ecosystem. The most recent wave of Linux admins are using ufw as well, mostly…
15
Show HN: Hextrap – Package Firewall with OPA Policies and MCP Support
用OPA策略和MCP支持的包防火墙，自动拦截恶意与废弃包，保障供应链安全。
We’re building Hextrap ( https://hextrap.com/products/firewall/ ), a package firewall to make it easier for teams and organizations to govern the pack…
16
Show HN: Agent Gate – a deterministic CI firewall for AI-generated PRs
一款针对AI生成PR的确定性CI防火墙，确保代码审查安全可靠
Article URL: https://github.com/sjh9714/Agent-Gate Comments URL: https://news.ycombinator.com/item?id=48524230 Points: 1 # Comments: 0
17
SentinelMCP – An open-source firewall for AI agents that use MCP
开源防火墙SentinelMCP，专为使用MCP协议的AI代理提供安全防护，填补AI安全工具空白。
Article URL: https://github.com/technosiveuk-ui/SentinelMCP Comments URL: https://news.ycombinator.com/item?id=48511652 Points: 1 # Comments: 0
18
Goal-Autopilot: A Verifiable Anti-Fabrication Firewall for Unattended Long-Horizon Agents
论文提出一种可验证的反伪造防火墙，让LLM代理在无人监督时无法虚报成功，将诚实作为自主任务的首要度量。
arXiv:2606.11688v1 Announce Type: cross Abstract: Long-horizon LLM agents are not trusted to run unattended: with no human watching, they confidently …
19
Helm AI Kernel, a fail-closed execution firewall for AI agents
AI代理的安全执行防火墙，确保fail-closed机制，保护你的Claude、Codex等工具。
Article URL: https://github.com/Mindburn-Labs/helm-ai-kernel Comments URL: https://news.ycombinator.com/item?id=48490524 Points: 2 # Comments: 0
20
Show HN: Built an open-source local firewall for AI coding agents
本地开源的AI编码代理防火墙，自动拦截超预算请求并执行安全策略，保障你的AI工具成本可控且安全。
GitHub: https://github.com/ashp15205/guardian-runtime Docs: https://ashp15205.github.io/guardian-runtime/ Hi Guys, I built Guardian Runtime: a local F…