Skip to content

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

Oct 12 · Monday

All papers

Found 3 papers
Filter3

Attack type

Poisoning and backdoors3

Attack technique

Automated search8Encoding and obfuscation4Defense-targeted4Dormant triggers3Selection manipulation3

System type

AI Agent5coding agent3

Attack surface / entry point

Tool and skill descriptions3Weights and gradients3Distribution channels4

Layer

Application layer3

System component

MCP and skills3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 261papers have no tags yet and are not included in filtered results.
Attack technique：Dormant triggersSystem type：coding agentAttack surface / entry point：Tool and skill descriptionsClear all

Another 261papers do not have category tags yet and are not included in filtered results.

  2. AttacksarXiv 2608.25776

    EvoMal 攻击利用自我进化编码 Agent 的自我投毒实现蠕虫式传播

    提出 EVOMAL，诱导自演化编码 Agent 在创建技能时自我投毒并蠕虫传播

    arXiv
    2608.25776
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Devstral-Small-2, Gemma-4-31B-IT, Qwen3-Coder-Next and others7

    Abstract论文指出了自演化智能体模仿检索代码的自我毒化漏洞，提出 EVOMAL 攻击与防御，阐明了供应链新风险。

    Paper analysisRead analysis
  3. AttacksarXiv 2608.09577

    ElasticBack：通过触发词与规则耦合在 LLM Agent 技能中植入条件后门

    提出 ElasticBack，在单个 Agent 技能中植入条件后门

    arXiv
    2608.09577
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    GLM-5.2, MiniMax-M3, GPT-5.4 and others4
    AbstractElasticBack 用冻结规则加遗传搜索演化 trigger，在单 skill 上做条件后门。

    ElasticBack 是放在 LLM agent 单个 skill 里的条件后门攻击。。

    Paper analysisRead analysis
You have reached the end