Skip to content

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

Oct 12 · Monday

All papers

Found 6 papers
Filter4

Attack type

Prompt injection3Poisoning and backdoors5

Attack technique

Gradient and representation optimization0Automated search17Encoding and obfuscation5Conversation structure manipulation1Defense-targeted7Dormant triggers5Selection manipulation10

Impact

Unauthorized actions3

System type

AI Agent5coding agent3

Attack surface / entry point

User input42Web pages and interfaces9Documents and messages12Tool responses8Tool and skill descriptions6Code repositories and dependencies6Retrieval corpus9Memory writes15Images, audio and video38Training data17Weights and gradients27Distribution channels18

Layer

Application layer5

System component

MCP and skills5
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 240papers have no tags yet and are not included in filtered results.
Attack technique：Gradient and representation optimizationAttack technique：Conversation structure manipulationAttack technique：Dormant triggersAttack surface / entry point：Tool and skill descriptionsClear all

Another 240papers do not have category tags yet and are not included in filtered results.

  4. AttacksarXiv 2608.25776

    EvoMal attack uses self-poisoning of self-evolving coding agents to achieve worm-like propagation

    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
  5. 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