Skip to content

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

Oct 12 · Monday

All papers

Found 6 papers
Filter5

Attack type

Jailbreaks3Prompt injection45Poisoning and backdoors34Extraction and theft1Detection evasion4Malicious use1

Attack technique

Automated search3Defense-targeted3

Defense type

Detection and filtering3

Impact

Unauthorized actions3

System type

AI Agent6coding agent4

Attack surface / entry point

User input33Web pages and interfaces3Documents and messages6Tool responses6Tool and skill descriptions6Code repositories and dependencies3Inter-agent messages4Images, audio and video4Distribution channels3

Layer

Application layer6

System component

MCP and skills6Guardrails and judges4
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 type：Extraction and theftAttack type：Detection evasionAttack type：Malicious useAttack surface / entry point：Tool and skill descriptionsLayer：Application layerClear all

Another 240papers 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. DefensesarXiv 2610.02432

    论文提出 LLM 输入扰动鲁棒性度量，并发布 ASA 攻击与 AttestMCP 防护

    提出 ASA 与 AttestMCP，度量并降低 LLM 对输入序列扰动的敏感

    arXiv
    2610.02432
    Published
    Layer
    Application layer
    Setting
    LLM applications, AI Agent
    Attacker
    Black-box
    Evaluated models
    Gemma-3-27B-Instruct, Gemma-3-4B-Instruct, Llama-3.2-3B-Instruct and others12
    Paper analysisRead analysis
  3. 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
  4. 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
  5. DefensesarXiv 2609.01677

    Skill-as-API：面向智能体软件工程的机密多智能体协作协议

    提出 Skill-as-API，隔离多智能体协作中的 skill 正文与系统提示词

    arXiv
    2609.01677
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems, coding agent
    Abstract协议把 skill 正文留在所有者侧，四层限制发现内容、权限期限和注入拼接。

    Skill-as-API 是面向智能体软件工程的协调协议，用来在跨组织调用时把 skill 的代码和系统提示词留在所有者进程。作者针对三条威胁：经通道或命名空间抽取专有方法，用注入让被调用模型输出系统提示词，以及协作结束后权限继续保留。

    Paper analysisRead analysis
  6. AttacksarXiv 2608.09732

    ColluSkill 用跨技能组合绕过 Agent 技能扫描器

    提出 ColluSkill，用跨技能组合绕过 Agent 技能扫描器

    arXiv
    2608.09732
    Published
    Layer
    Application layer
    Setting
    coding agent
    Attacker
    Black-box, Gray-box
    Evaluated models
    GPT-5.5, DeepSeek-V4-Pro, GLM-5.2

    Abstract论文揭示了单技能孤立扫描的盲区，提出多技能链攻击 ColluSkill 与上下文防御 ChainGuard 并验证了有效性。

    Paper analysisRead analysis
You have reached the end