1
Astartis x Codex
围绕证据的企业级开发者安全控制平面，助力团队高效管控开发安全与合规讨论。
Enterprise developer security control plane around evidence Discussion | Link
2
Temporary Authority, Permanent Effects: Commit-Time Authorization for LLM Agents
LLM代理权限管理新思路：提交时授权，临时权限却产生持久效果，能控制失效并保留用户目标。
arXiv:2607.10487v1 Announce Type: cross Abstract: LLM agents can commit durable effects from authority evidence that was valid earlier in execution: a…
3
Neuro-Agentic Control: A Deep Learning-based LLM-Powered Agentic AI Framework for Controlling Security Controls
LLM与深度学习融合框架，驱动智能代理守护工业物联网安全，突破传统规则监控瓶颈。
arXiv:2607.09076v1 Announce Type: new Abstract: Cyberattacks on operational technology are increasingly causing costly downtime and physical damage, e…
4
Show HN: Scan your AI agents for dangerous capabilities
开源项目，用默认拒绝、人工审批和加密审计追踪锁定AI代理危险行为，杜绝自授权漏洞。
Article URL: https://github.com/makerchecker/MakerChecker Comments URL: https://news.ycombinator.com/item?id=48804182 Points: 16 # Comments: 8
5
Show HN: Deconstructing Anthropic's Coding Agent Control Model
拆解Anthropic如何端到端管控Claude编码代理，并告诉你如何在自己的开发环境中复制这套安全边界。
Anthropic recently published an excellent write-up on how they contain Claude Code and its sub-agents. One thing that stood out is that the architectu…
6
A Low-Rank Subspace Analysis of LLM Interventions
从副作用的根源剖析LLM行为干预，低秩子空间分析精准定位，为安全控制提供新视角
arXiv:2606.14388v1 Announce Type: new Abstract: Interventions designed to modify a particular behavior in LLMs, such as refusal or sycophancy, often p…
7
GateGraph – a gate that decides if an AI agent action may proceed before it runs
专为AI代理设计的门控系统GateGraph，能在动作执行前决定是否放行，保障安全与可控性。
Article URL: https://github.com/humancoreai/Gategraph Comments URL: https://news.ycombinator.com/item?id=48251003 Points: 1 # Comments: 0