Skip to content

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

Oct 12 · Monday

All papers

Found 15 papers
Filter5

Attack type

Prompt injection15Poisoning and backdoors4

Attack technique

Automated search3

Defense type

Instruction–data separation3

Impact

Harmful content6Unauthorized actions82Data and privacy leaks15Output manipulation21Availability and reliability3Oversight failure3

System type

AI Agent15coding agent3

Attack surface / entry point

User input15Web pages and interfaces6Documents and messages8Tool responses9Tool and skill descriptions11Code repositories and dependencies3Memory writes9Inter-agent messages6Distribution channels7

Layer

Application layer15

System component

MCP and skills4Memory4Permissions and sandboxing3
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.
Impact：Data and privacy leaksSystem type：AI AgentSystem type：coding agentAttack surface / entry point：Documents and messagesAttack surface / entry point：Tool responsesClear all

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

  3. DefensesarXiv 2609.33371

    论文提出保险库中介执行边界，评估 LLM Agent 的 API 凭据处理风险

    提出并评测保险库中介执行边界，隔离 Agent 的 API 凭据

    arXiv
    2609.33371
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Corvic Security Vault
    Abstract作者称，凭据分离可减少披露路径，但权限、操作授权和配置验证仍需独立控制。

    这是一项智能体 API 凭据威胁分析及 Vault 执行边界的功能评测。作者关心的不是模型能否承诺保密，而是认证材料是否会进入模型、日志、记忆和执行代码。

    Paper analysisRead analysis
  4. AttacksarXiv 2609.27542

    Researchers use control token injection to delete gpt-oss-20b's reasoning chain and bypass chain-of-thought monitoring

    提出控制标记注入，清空工具 Agent 的思维链以绕过推理监控

    arXiv
    2609.27542
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    openai/gpt-oss-20b, google/gemma-4-26B-A4B-it, deepseek-ai/DeepSeek-R1-Distill-Qwen-7B and others4

    Abstract论文阐明控制标记注入可抑制 CoT 使监控失效并促成拒绝绕过，且工具执行受解析器宽容度影响。

    Paper analysisRead analysis
  5. AttacksarXiv 2609.18217

    研究：跨通道碎片化攻击可绕过 MCP 单通道防御

    提出跨通道分段攻击，利用 MCP 隐式信任外发敏感文件

    arXiv
    2609.18217
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    GPT-4o, GPT-4o-mini, GPT-5.4 and others15

    Abstract论文揭示了 MCP 多通道隐式信任层级，通过跨通道分段与协议级利用突破现有防御，展示了严重的凭证外发风险。

    Paper analysisRead analysis
  6. AttacksarXiv 2609.13889

    PMPA：针对 OpenClaw 与 Claude Code 的持久记忆投毒攻击

    提出 PMPA，经外部源向 Agent 持久记忆投毒并跨会话泄露隐私

    arXiv
    2609.13889
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    DeepSeek-V4-Flash, DeepSeek-V4-Pro, Qwen3-Max

    Abstract论文提出了持久记忆投毒攻击 PMPA，报告了 harness 智能体在处理外部数据时易受跨会话记忆投毒与隐私泄露的风险。

    Paper analysisRead analysis
  8. DefensesarXiv 2609.04875

    Forgetting without restart: execution-state forgetting for stateful LLM agents

    Proposes execution-state forgetting, using provenance-guided selective replay to purify stateful agents

    arXiv
    2609.04875
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Llama-3.1-8B-Instruct, Qwen2.5-7B-Instruct, Mistral-7B-Instruct-v0.3
    AbstractSelective replay concatenates the clean prefix with the sanitized suffix, and main-table metrics match full reset.

    This work defines forgetting in long-horizon agents as runtime counterfactual equivalence, rather than deleting a plaintext memory.

    Paper analysisRead analysis
  9. DefensesarXiv 2608.24017

    WebMCP-Phalanx：为浏览器内 LLM Agent 工具调用建立信任边界

    提出 WebMCP-Phalanx，用能力凭证与双智能体隔离浏览器工具调用

    arXiv
    2608.24017
    Published
    Layer
    Application layer
    Setting
    web agent
    AbstractPhalanx 用浏览器凭证绑定工具所有权，Q/P 分离拦住描述注入，工具名与返回值仍有残留。

    WebMCP-Phalanx针对浏览器里的 WebMCP 智能体：在 SOP 下补工具所有权，并把语义检查从有工具权的执行中分开。

    Paper analysisRead analysis
  13. 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

    arXiv
    2605.17380
    Published
    Layer
    Application layer
    Setting
    coding agent

    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
  14. Evaluation and benchmarksarXiv 2605.01970

    Trojan Hippo Bench: A Dynamic Benchmark for Persistent Memory Attacks and Defenses on LLM Agents

    构建 Trojan Hippo Bench，评测 Agent 持久记忆投毒与外泄

    arXiv
    2605.01970
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Gemini 3.1 Pro, GPT-5-mini, GPT-5

    Abstract论文提出了评测智能体持久化记忆攻击与防御的 Trojan Hippo Bench，揭示了潜伏攻击威胁及内存防御的安全与效用权衡。

    Paper analysisRead analysis
You have reached the end