Skip to content

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

Oct 12 · Monday

All papers

Found 6 papers
Filter3

Attack type

Prompt injection3Poisoning and backdoors5

Attack technique

Defense-targeted3

Impact

Unauthorized actions4

System type

AI Agent6

Attack surface / entry point

User input19Web pages and interfaces4Documents and messages5Tool responses8Tool and skill descriptions10Code repositories and dependencies3Memory writes3Inter-agent messages3Images, audio and video3Distribution channels6

Layer

Application layer5

System component

MCP and skills36Memory3Guardrails and judges6Monitors4Permissions and sandboxing7Fine-tuning and open weights6
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.
System type：AI AgentAttack surface / entry point：Distribution channelsSystem 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. AttacksarXiv 2609.39607

    Pretext 攻击绕过 NVIDIA SkillSpector 等 Agent 技能扫描器

    提出 PRETEXT 攻击，迭代改写技能文本绕过技能扫描器并让 Agent 执行木马

    arXiv
    2609.39607
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Attacker
    White-box
    Evaluated models
    glm (z-ai/glm-5.1), qwen3t (qwen/qwen3-235b-a22b-thinking-2507), gpt-oss (openai/gpt-oss-120b)
    Abstract论文提出了针对多阶段技能检测器的白盒攻击，揭示了单纯依赖大模型自适应检测的局限。

    PRETEXT 是一项针对基于“静态规则加语义大模型”的智能体技能安全检测框架的白盒攻击与协同进化评估研究。

    Paper analysisRead analysis
  3. 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
  5. 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
  6. AttacksarXiv 2604.03890

    从提示到物理动作：针对 LLM 中介机器人控制系统的结构化后门攻击

    提出结构化 JSON 后门，经投毒 LoRA 在机器人控制中触发恶意动作

    arXiv
    2604.03890
    Published
    Layer
    Training and data layer
    Setting
    Embodied systems and robotics, LLM applications
    Evaluated models
    Llama-3.1-8B-Instruct, Gemma-2-9B-IT, DeepSeek-R1-Distill-Llama-8B and others4

    Abstract推理层后门传不到执行。

    Paper analysisRead analysis
You have reached the end