Skip to content

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

Oct 12 · Monday

All papers

Found 7 papers
Filter4

Model risks

Dangerous agent actions4

Defense type

Detection and filtering4Instruction–data separation2Permissions and approval5Monitoring and auditing4

Impact

Unauthorized actions7Data and privacy leaks4

System type

AI Agent61coding agent7web agent5Browser and computer use3Multi-agent systems5

Layer

Application layer7

System component

Permissions and sandboxing3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 265papers have no tags yet and are not included in filtered results.
Defense type：Instruction–data separationDefense type：Permissions and approvalImpact：Unauthorized actionsSystem type：coding agentClear all

Another 265papers do not have category tags yet and are not included in filtered results.

  2. 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
  3. Analysis and theoryarXiv 2610.04375

    Paper reveals that LLM agent tool calls are rewritten during execution paths, and proposes IntAct as a fix

    提出 IEC 与 IntAct，测量并修复 Agent 工具调用的路径篡改

    arXiv
    2610.04375
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    qwen3-coder-plus, Qwen2.5-Coder-32B, Qwen2.5-72B and others4

    Abstract论文界定工具调用在执行路径中的意图偏离问题，提出无执行归因协议与跳级修复，为智能体工程提供评测与设计准则。

    Paper analysisRead analysis
  4. DefensesarXiv 2609.38983

    论文提出 Approval Laundering 分类，实测 Claude Code 审批与执行绑定失败

    形式化编程 Agent 的审批洗白并提出 HMAC 权能令牌防御

    arXiv
    2609.38983
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Claude Code (v2.1.197, opus[1m] / claude-sonnet-5-ccmax), Codex CLI (@openai/codex v0.154.0)

    Abstract系统揭示编程智能体审批洗白风险，提出七字段权能防御机制，证实其能消除身份时序偏离但难防副作用偏离。

    Paper analysisRead analysis
  6. 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
You have reached the end