Skip to content

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

Oct 12 · Monday

Agent safety · Papers

Found 4 papers
Filter1

Attack type

Prompt injection3

Impact

Output manipulation3

System type

AI Agent4

Attack surface / entry point

User input6Tool responses4Tool and skill descriptions5Inter-agent messages3

Layer

Application layer4

System component

Permissions and sandboxing3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.
Attack surface / entry point：Tool responsesTopic: Agent safetyClear all
  1. AttacksarXiv 2609.11757

    Researchers disclose a Whisper prompt injection attack on the AP2 payment protocol and propose the A-VIP defense

    提出 AP2 支付协议的 Whisper 攻击与 A-VIP 绑定防御

    arXiv
    2609.11757
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    gemini-2.5-flash-lite, gemini-3.1-flash-lite, gemini-3-flash-preview and others15

    Abstract论文揭示了 AP2 协议决策层受操纵的风险，提出结构化与权能绑定防御 A-VIP，并发布评测基准。

    Paper analysisRead analysis
  2. AttacksarXiv 2608.29381

    Researchers propose five categories of safety failures in agent checkpoint rollback and implement three attacks on Hermes, Cline, and LangGraph

    提出利用检查点回滚破坏 Agent 执行连续性的攻击

    arXiv
    2608.29381
    Published
    Layer
    Application layer
    Setting
    AI Agent

    Abstract论文系统研究了智能体 C/R 的安全性，分析了合法回滚破坏执行连续性的机理，并实证评估了其普遍性与危害。

    Paper analysisRead analysis
  4. AttacksarXiv 2607.12507

    研究者提出 RARE 攻击：LLM 辅助逆向工程中的表示混淆

    提出 RARE-Guard，阻止逆向观察被提升为指令或已验证声明

    arXiv
    2607.12507
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    gpt-5.5, claude-sonnet-4-6, gemini-2.5-pro and others5
    Abstract成对二进制衡量无效提升。

    作者定义的失败是：LLM 辅助逆向中，忠实提取的二进制观察获得它并未赢得的指令权限、声明证据或可信状态。

    Paper analysisRead analysis
You have reached the end