Skip to content

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

Oct 12 · Monday

Agent safety · Papers

Found 5 papers
Filter2

Attack type

Prompt injection3

Impact

Unauthorized actions3

System type

AI Agent5

Attack surface / entry point

User input6Documents and messages0Tool responses4Tool and skill descriptions5Inter-agent messages3

Layer

Application layer5

System component

MCP and skills4Permissions and sandboxing4
Select any value within a category; different categories must all match. Counts include the other filters you have selected.
Attack surface / entry point：Documents and messagesAttack surface / entry point：Tool and skill descriptionsTopic: Agent safetyClear all
  1. AttacksarXiv 2610.02432

    论文提出 LLM 输入扰动鲁棒性度量，并发布 ASA 攻击与 AttestMCP 防护

    提出 ASA 与 AttestMCP，度量并降低 LLM 对输入序列扰动的敏感

    arXiv
    2610.02432
    Published
    Layer
    Application layer
    Setting
    LLM applications, AI Agent
    Attacker
    Black-box
    Evaluated models
    Gemma-3-27B-Instruct, Gemma-3-4B-Instruct, Llama-3.2-3B-Instruct and others12
    Paper analysisRead analysis
  4. 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
You have reached the end