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

Jailbreaks10Prompt injection30Poisoning and backdoors8Detection evasion11

Attack technique

Defense-targeted4

Defense type

Detection and filtering4

Impact

Unauthorized actions4Output manipulation3

System type

AI Agent7

Attack surface / entry point

Tool responses3Tool and skill descriptions5Distribution channels4

Layer

Application layer8Training and data layer3

System component

MCP and skills40Memory38RAG20Guardrails and judges8Monitors6Permissions and sandboxing11Fine-tuning and open weights3Embeddings3
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.
Attack type：Poisoning and backdoorsLayer：Application layerSystem component：Guardrails and judgesClear all

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

  1. AttacksarXiv 2610.10612

    PyCache Trap 利用 Python 缓存替换绕过七款 Agent Skill 扫描器

    提出 PyCache Trap，用字节码缓存替换绕过 Agent 技能扫描器

    arXiv
    2610.10612
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    CISCO, HSS, AUDITOR and others8
    Abstract论文剖析智能体技能审查与执行脱节盲区，提出 PyCache Trap 攻击并构建基于可信复现的 EAV 防御。

    这篇论文研究了智能体技能（Agent Skills）安全扫描中的“审查–执行脱节”问题，并提出了对应的攻击验证与防御方案。

    Paper analysisRead analysis
  2. DefensesarXiv 2610.07657

    DEFER1 多智能体防御研究报告受控测试中的攻击成功率下降

    实现 DEFER，以确定性检查优先拦截多智能体流水线的内容攻击

    arXiv
    2610.07657
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    Qwen3-235B-A22B-Instruct-2507, gpt-oss-120b, Llama-4-Scout-17B-16E-Instruct and others5
    AbstractDEFER 把确定性检查放在 judge 之前。

    DEFER 用来测量多智能体授权流水线里，确定性规则在何处结束、LLM judge 从何处开始。

    Paper analysisRead analysis
  4. AttacksarXiv 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
  8. 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
You have reached the end