Skip to content

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

Oct 12 · Monday

All papers

Found 13 papers

Another 232papers 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

    Published
    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. AgentSpy: Observing AI agent behavior at the system call layer and detecting skill injection attacks

    提出 AgentSpy,在系统调用层观测 Agent 行为并检测技能注入

    Published
    Evaluated models
    gpt-5.6-terra, deepseek-v4-flash, glm-5.3-flash and others4
    Abstract提出了系统级智能体监控框架 AgentSpy,揭示出通过测试背后的非预期行为与注入风险。

    本研究提出了面向 AI 智能体的系统级外部监控与行为分析框架 AgentSpy。

    Paper analysisRead analysis
  3. DefensesarXiv 2609.36879

    SKILLLITE:用小模型做证据引导的恶意 Agent Skill 审计

    提出证据引导的 SKILLLITE,审计部署前恶意 Agent Skill

    Published
    Setting
    AI Agent
    Evaluated models
    Gemma4:e4b, Qwen3.5:9B, DeepSeek-R1:8B and others4
    AbstractSKILLLITE 把证据抽取外置,让紧凑 LLM 只做意图条件下的风险裁决,三个基准上 F1 高于所列基线。

    SKILLLITE是面向紧凑、可本地部署 LLM 的恶意 Agent Skill 预执行审计框架,作者单位为南洋理工大学。

    Paper analysisRead analysis
  4. DefensesarXiv 2609.30657

    研究者提出面向邮件 Agent 的攻击链建模提示注入检测框架

    提出面向邮件 Agent 的攻击链提示注入检测框架

    Published
    Setting
    AI Agent
    Evaluated models
    Proposed framework
    Abstract攻击链与动作一致性融合改善了严格检测的平均 F1,但迁移、误报和攻击召回仍需分别看。

    这是一项邮件智能体提示注入防御的离线建模与评测研究:作者把攻击文本是否恶意、攻击是否推进到工具操作、最终参数是否达标分开处理。

    Paper analysisRead analysis
  5. AttacksarXiv 2609.22510

    特拉维夫大学提出爆炸性提示词:条件触发的间接提示注入可绕过九款生产 Agent

    提出条件触发的爆炸提示词,并设计摄入期检测器 DeFuse

    Published
    Setting
    AI Agent
    Evaluated models
    Llama-3.1-8B-Instruct, Llama-3.1-70B-Instruct, Qwen2.5-32B-Instruct and others15
    Abstract论文揭示了条件触发使提示注入绕过防御并在触发时执行工具,提出轻量检测器并在摄入期有效防范。

    论文针对大语言模型智能体面临的间接提示注入威胁,研究了利用条件句式实现时间分离的爆炸提示词。

    Paper analysisRead analysis
  6. DefensesarXiv 2608.03485

    SkillSentry:用自适应蜜罐世界动态检测 Agent 技能安全

    提出 SkillSentry,用自适应蜜罐世界在安装前检测 Agent 技能是否越出能力契约

    Published
    Setting
    AI Agent
    Evaluated models
    DeepSeek-V4-Pro, Qwen, Kimi and others4
    Abstract契约加配对执行审计技能越权。

    SkillSentry 是安装前的动态技能审计,用来发现超出宣称功能的能力漂移。技能一旦安装,就能使用宿主的文件、shell、凭证和网络,而有害分支可能要等特定资源才出现。作者认为,源码或一次性语义判断既不能确认分支会执行,也不能把技能造成的效果与任务或基座智能体的动作分开。

    Paper analysisRead analysis
  7. AttacksarXiv 2607.06595

    When Agents Remember Too Much: Memory Poisoning Attacks against Large Language Model Agents

    Proposed GhostWriter memory poisoning, which writes into the agent's long-term memory via email and calendar and activates across sessions

    Published
    Setting
    AI Agent
    Evaluated models
    GPT-5.4-mini, DeepSeek-V4-Flash, Gemini-2.5-Flash and others4
    Paper analysisRead analysis
  8. DefensesarXiv 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

    Published

    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
  9. DefensesarXiv 2603.04474

    From Spark to Wildfire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration

    Proposing a lineage-graph governance layer to suppress error cascades in multi-agent collaboration

    Published
    AbstractA single seed can solidify into a false consensus along a fixed collaboration graph.

    The authors turn "small errors becoming collective false consensus" in LLM-MAS into a measurable propagation on a graph, and use a plug-in that only changes messages, not topology, to reduce the final infection.

    Paper analysisRead analysis
  10. WAInjectBench 系统评测网页 Agent 的提示注入检测方法

    提出 WAInjectBench 评测网页 Agent 的提示注入检测

    Published
    Setting
    web agent
    Evaluated models
    GPT-4o, Mistral-7B-Instruct-v0.1, Llama-Prompt-Guard-2-86M and others8
    AbstractWAInjectBench 比较网页智能体的提示注入检测:显式线索可被部分检出,隐蔽攻击大多漏检。

    WAInjectBench 是网页智能体提示注入检测的基准。作者要看现有检测器能否发现这类攻击:攻击者改网页,使智能体执行目标动作,而不是用户任务。作者称这是首个此类综合基准。

    Paper analysisRead analysis
You have reached the end