ZitPit:面向代理软件摄入的消费者侧准入控制
ZitPit: Consumer-Side Admission Control for Agentic Software Intake
AI总结:
ZitPit通过严格边界控制,确保首次见到的外部工件成为持久政策事件,统一了工件准入、仓库开放状态、能力范围执行和持久政策记录,提升代理工作流的安全性。
摘要:
AI IDEs和编码代理将发现、获取、工作区打开、安装和执行压缩成一个低可观测性循环。现有防御如溯源框架、包和仓库防火墙、运行时保护和工具批准提示各自覆盖该路径的一部分,但常使最终消费者侧执行决策隐含。ZitPit是一个100%开源的Rust系统,主张更严格的边界:首次见到的外部工件应在获得受保护开发者或CI主机执行权限前成为持久政策事件。当前公开证据有意狭窄且明确,包括重复的Git smart-HTTP摄入测量,显示批准的工件比未管理的公共获取更快,加上实施的受保护会话和受管出站证明家族。更广泛的贡献是架构而非普遍覆盖的:ZitPit在消费者执行边界统一了工件准入、仓库开放状态、能力范围执行和持久政策记录,以提升代理工作流的安全性。
英文摘要:
AI IDEs and coding agents compress discovery, fetch, workspace open, installation, and execution into one low-observability loop. Existing defenses such as provenance frameworks, package and repository firewalls, runtime protection, and tool-approval prompts each cover part of that path, but they often leave the final consumer-side execution decision implicit. ZitPit is a 100% open-source Rust system that argues for a stricter boundary: first-seen external artifacts should become durable policy events before they gain execution rights on protected developer or CI hosts. The current public evidence is intentionally narrow and explicit. It includes repeated Git smart-HTTP intake measurements showing that approved artifacts can remain faster than unmanaged public fetch, plus implemented protected-session and governed-egress proof families. The broader contribution is architectural rather than universal-coverage-by-assertion: ZitPit unifies artifact admission, repo-open state, capability-scoped execution, and durable policy records at the consumer execution boundary for agentic workflows.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。