Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
Another 230 papers do not have category tags yet and are not included in filtered results.
“
About this collection Collection in progress We are building a large AI safety paper collection to help researchers find work related to their interests. Papers are collected automatically andfiltered only for relevance to AI safety , without judging quality, novelty or reading value. The default “Annotated first” shows papers with tags or published paper analyses first. Each group is ordered by original publication date, newest first, with undated papers last. “Newest first” uses publication dates only. This order is not a quality ranking.
One-line summaries, tags and paper analyses are prepared by AI from the papers. Language models may have systematic biases and produce hallucinations.We plan to carry out human annotation and review to reduce errors in this content.
提出 Tracekit，审计编码 Agent 的意图、推理与动作并检测账本篡改
Published Sep 29
Evaluated models Claude Code (claude -p, version 2.1) , 独立评审（同一 CLI，无工具） Abstract Tracekit 把意图、自述和动作写入可锚定的哈希链。Tracekit 是无第三方依赖的编码智能体审计层：把人类请求、模型自述和已执行动作并排写入可外部锚定的哈希链，执行前用正则门，事后用规则和独立模型互查。
提出可验证操作卡 VAC，把智能体浏览器确认绑定到真实 DOM 操作
Published Sep 16
Evaluated models gpt-oss-120b , Gemini-2.5-Flash , GPT-4.1 and others6 提出 Skill-as-API，隔离多智能体协作中的 skill 正文与系统提示词
Published Sep 1 Abstract 协议把 skill 正文留在所有者侧，四层限制发现内容、权限期限和注入拼接。Skill-as-API 是面向智能体软件工程的协调协议，用来在跨组织调用时把 skill 的代码和系统提示词留在所有者进程。作者针对三条威胁：经通道或命名空间抽取专有方法，用注入让被调用模型输出系统提示词，以及协作结束后权限继续保留。
提出 WebMCP-Phalanx，用能力凭证与双智能体隔离浏览器工具调用
Published Aug 25 Abstract Phalanx 用浏览器凭证绑定工具所有权，Q/P 分离拦住描述注入，工具名与返回值仍有残留。WebMCP-Phalanx 针对浏览器里的 WebMCP 智能体：在 SOP 下补工具所有权，并把语义检查从有工具权的执行中分开。
提出 ClawSentry 多层监控网关，在技能准入和运行时拦截恶意技能与隐藏指令
Published Aug 21
Evaluated models Codex/GPT-5.4 , Codex/GPT-5.5 , Claude Code/GLM-5.1 and others6 Abstract ClawSentry 用包准入、三级运行时门控和反绕过，压低 skill 攻击并保住干净任务。ClawSentry 是挂在智能体运行时之外的安全监督网关，用来同时盖住 skill 执行的多个生命周期边界，并把已被拒绝的效果记到会话里。
Proposes a static-first validator, CARE, that decides before dispatch whether an agent's shell command may be executed
Published Jul 22 Proposes Prismata, which uses critical-path annotation and mechanical isolation to constrain cross-site prompt injection in web agents.
Published Jul 9
Evaluated models gpt-5.4-mini , gpt-5.4 , gpt-5.4-nano and others7 You have reached the end