Skip to content

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

Oct 12 · Monday

All papers

Found 8 papers
Filter3

Attack type

Prompt injection7Poisoning and backdoors8

Impact

Unauthorized actions4

System type

AI Agent8coding agent5

Attack surface / entry point

User input37Web pages and interfaces19Documents and messages25Tool responses23Tool and skill descriptions14Code repositories and dependencies7Retrieval corpus8Memory writes11Inter-agent messages8Images, audio and video7Weights and gradients1Distribution channels8

Layer

Application layer8

System component

MCP and skills8
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 232papers have no tags yet and are not included in filtered results.
Attack surface / entry point：Weights and gradientsAttack surface / entry point：Distribution channelsLayer：Application layerClear all

Another 232papers do not have category tags yet and are not included in filtered results.

  1. Evaluation and benchmarksarXiv 2609.35912

    MMSkillRisk：多模态技能图像中的隐藏指令可诱导 Agent 执行未授权操作

    提出 MMSkillRisk 基准，评测多模态技能图像中的隐藏指令诱导 Agent 越权操作

    arXiv
    2609.35912
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    GPT-5.6-sol, Kimi-K2.6, Kimi-K3 and others6

    Abstract论文提出 MMSkillRisk 基准与 NCVA 攻击，揭示多模态技能中教学图像潜藏指令可引发未授权操作并与良性任务共存。

    Paper analysisRead analysis
  2. Evaluation and benchmarksarXiv 2609.30383

    研究者提出技能级联攻击

    提出技能级联攻击，把有害目标拆散到多个技能里绕过单技能扫描

    arXiv
    2609.30383
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    GPT-5.4, GPT-5.4 Mini, Claude Opus 4.6 and others11

    Abstract论文探讨了多技能智能体系统面临的技能级联攻击风险，提出自动化红队框架与基准集，指出跨技能交互存在安全防护盲区。

    Paper analysisRead analysis
  3. Evaluation and benchmarksarXiv 2609.28915

    研究提出 ACE 语料库，评估内核级证据对 Agent 安全检测的有效性

    构建 ACE 语料，评测内核级证据对 Agent 攻击检测的有效性

    arXiv
    2609.28915
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    AdaBoost, XGBoost, TabPFN and others10
    AbstractACE 用配对的内核与应用层证据表明，syscall 痕迹可判别智能体攻击，两层组合通常更好。

    ACE 是一份把智能体会话的内核 syscall 痕迹与应用层清单、转录配对起来的检测语料和基准。。

    Paper analysisRead analysis
  4. Evaluation and benchmarksarXiv 2608.06862

    SynChain：诱导计算机使用 Agent 自建攻击链并跨任务持久化

    提出 SYNCHAIN，诱导计算机使用 Agent 自建跨任务持久攻击链

    arXiv
    2608.06862
    Published
    Layer
    Application layer
    Setting
    Browser and computer use, coding agent
    Evaluated models
    Qwen3.5-9B, Llama-3.1-8B, Ministral-3-8B

    Abstract论文揭示了 CUA 自合成工件带来的内部供应链威胁，验证了潜伏载荷的跨任务传播能力与防御局限。

    Paper analysisRead analysis
  6. Evaluation and benchmarksarXiv 2607.13987

    Agent Skill Safety: Threat Models, Attacks, Defenses, and Evaluation

    用 SkillSec-Eval 评测 Agent 技能全生命周期安全

    arXiv
    2607.13987
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Gemini 3.1 pro, Gemini 1.5 Flash
    AbstractSkillSec-Eval 按五个信任边界评测可复用技能，作者称单点防御不足以覆盖全生命周期。

    SkillSec-Eval 按信任边界评测可复用智能体技能，而不是只看提示注入或单次执行。技能被共享后，元数据、权限、工作流和版本可独立于底层模型变化。作者要回答的是：恶意技能能否在准入、检索、规划、执行或更新阶段穿过未经验证的信任边界。

    Paper analysisRead analysis
  7. Evaluation and benchmarksarXiv 2606.15899

    SkillVetBench：用 LLM-as-Judge 评估开源 LLM Agent 技能的多维安全风险

    提出 SkillVetBench 评估开源 Agent 技能的多维安全风险

    arXiv
    2606.15899
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Qwen2.5-14B-Instruct, Qwen2.5-32B, Llama-3.1-70B and others6

    Abstract公开排行榜用 LLM-as-Judge 给技能分列 SARS 与 CVSS，并对照市场官方审查。

    Paper analysisRead analysis
  8. Evaluation and benchmarksarXiv 2605.17380

    Uber proposes ADR enterprise-level agent detection system, deployed on 7,200 hosts for ten months

    提出企业级检测系统 ADR，识别编程 Agent 的提示注入与恶意 MCP

    arXiv
    2605.17380
    Published
    Layer
    Application layer
    Setting
    coding agent

    Abstract提出了端点因果遥测、两级在线分流与离线红队闭环的 ADR 系统，并在生产环境中验证了有效性。

    Paper analysisRead analysis
You have reached the end