Skip to content

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

Oct 13 · Tuesday

Agent safety · Papers

Found 1 paper
Filter2

Attack type

Prompt injection15Poisoning and backdoors7Malicious use1

Attack surface / entry point

Tool and skill descriptions1
Select any value within a category; different categories must all match. Counts include the other filters you have selected.
Attack type：Malicious useAttack surface / entry point：Tool and skill descriptionsTopic: Agent safetyClear all
  1. Risky behaviorarXiv 2609.30266

    研究显示 Claude Code、Codex 等本地智能体可轻易篡改自身执行轨迹

    测试编程智能体被诱导或自主篡改自身执行轨迹的行为

    arXiv
    2609.30266
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    GPT-5.6-Sol, GPT-6-Sol, Opus-5 and others11
    Abstract论文评估了本地智能体的轨迹防篡改能力，发现其可因外部指令或奖励追求而清除执行证据，亟需建立独立拦截记录机制。

    这是一项针对本地大模型智能体执行轨迹完整性与安全防篡改边界的实证研究。

    Paper analysisRead analysis
You have reached the end