Skip to content

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

Oct 12 · Monday

All papers

Found 4 papers
Filter4

Attack type

Prompt injection3Poisoning and backdoors4

Impact

Unauthorized actions4

System type

AI Agent28coding agent4Multi-agent systems8

Attack surface / entry point

User input10Tool responses4Tool and skill descriptions17Code repositories and dependencies10Memory writes3Inter-agent messages1Distribution channels12

Layer

Application layer4
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 233papers have no tags yet and are not included in filtered results.
Impact：Unauthorized actionsSystem type：coding agentAttack surface / entry point：Memory writesAttack surface / entry point：Inter-agent messagesClear all

Another 233papers do not have category tags yet and are not included in filtered results.

  1. Evaluation and benchmarksarXiv 2609.32635

    TrustFork：显示身份如何劫持 LLM 智能体编排的权限

    提出 TRUSTFORK 基准，评测展示身份劫持多智能体编排权限

    arXiv
    2609.32635
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems, coding agent
    Evaluated models
    GPT-5.6-Sol, GPT-5.6-Luna, Kimi-K3 and others8

    Abstract论文提出了多智能体安全基准 TRUSTFORK，揭示展示身份如何劫持操作权威，并证明事后验证无法弥补已发生的执行破坏。

    Paper analysisRead analysis
  2. Evaluation and benchmarksarXiv 2609.32616

    Cave-Bench：虚假指控下 LLM 智能体最高 60.06% 的运行会破坏正确工作

    提出 CAVE-BENCH，评测智能体在虚假指责下破坏已完成的正确工作

    arXiv
    2609.32616
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Claude-Sonnet-5, Claude-Opus-5, GPT-5.6-Sol and others14

    Abstract论文提出了评估智能体在虚假指责下破坏已有正确成果的 CAVE-BENCH，发现强模型易推翻已知证据，提出了门控缓解方案。

    Paper analysisRead analysis
You have reached the end