Skip to content

Translation in progress Some entries still include text in the original language.

Oct 12 · Monday

All papers

Found 8 papers
Filter4

Attack type

Prompt injection4Poisoning and backdoors4

Defense type

Monitoring and auditing4

Impact

Unauthorized actions8Data and privacy leaks5Oversight failure12

System type

AI Agent46coding agent8Browser and computer use3Multi-agent systems4Embodied systems and robotics3

Attack surface / entry point

User input3Tool and skill descriptions4

Layer

Application layer8

System component

MCP and skills14Memory3Guardrails and judges4Monitors5Permissions and sandboxing5
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 261papers have no tags yet and are not included in filtered results.
Impact：Unauthorized actionsSystem type：coding agentSystem component：MemorySystem component：MonitorsClear all

Another 261papers do not have category tags yet and are not included in filtered results.

  1. DefensesarXiv 2610.05241

    StateWise：在 Agent 执行动作前诊断并修复持久操作状态

    提出 StateWise，在编码智能体行动前诊断并修复失效持久状态

    arXiv
    2610.05241
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    GPT-5.6-sol, DeepSeek v4 Pro, Qwen 3.7 Max and others4
    AbstractStateWise 在动作前修复失效的持久前提。

    StateWise 是在执行带副作用的动作之前，诊断并修复编码智能体持久操作状态的框架。

    Paper analysisRead analysis
  2. DefensesarXiv 2610.05163

    Researchers construct segmented prompt injection on Claude Code and Codex and release a boundary action audit benchmark

    提出 PAA 方法，在边界动作前审计长流程智能体的分阶段提示注入

    arXiv
    2610.05163
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Claude Code (v2.1.172, Claude Sonnet 5), Codex CLI (v0.144.0, GPT-5.5)
    Abstract论文针对长流程注入提出边界动作审计与 PAA，在保持低误阻的同时实现高拦截率。

    本研究针对长流程智能体在执行任务时面临的分阶段间接提示注入威胁，提出了在动作生效前进行拦截的边界动作审计框架与路径对齐归因方法。

    Paper analysisRead analysis
  5. DefensesarXiv 2608.21101

    ClawSentry：面向自主 LLM Agent 的渐进式多层安全监控网关

    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

    arXiv
    2608.21101
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Codex/GPT-5.4, Codex/GPT-5.5, Claude Code/GLM-5.1 and others6
    AbstractClawSentry 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。

    Paper analysisRead analysis
  7. DefensesarXiv 2606.22673

    Agent MechSuits：面向多轮 CLI Agent 的机制子空间安全引导

    提出 Agent MechSuits，对多轮 CLI Agent 做步级检测与子空间转向

    arXiv
    2606.22673
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    LLaMA-3.1-8B, Qwen-2.5-7B, Gemma-2-9B
    Abstract白盒步级探针加稀疏转向可压低三模型恶意动作，同时提高生成崩溃率。

    Agent MechSuits 是面向多轮 CLI 智能体的白盒、步级表示防御，并配有可执行轨迹基准 MAS。

    Paper analysisRead analysis
You have reached the end