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

Oct 13 · Tuesday

All papers

Found 68 papers

Filter4

Attack type

Jailbreaks3 Prompt injection46 Poisoning and backdoors39 Detection evasion5

Attack technique

Automated search17 Encoding and obfuscation7 Defense-targeted8 Dormant triggers8 Selection manipulation10

Defense type

Detection and filtering10 Instruction–data separation12 Permissions and approval10 Monitoring and auditing5

Impact

Unauthorized actions41 Data and privacy leaks13 Output manipulation6 Availability and reliability3

System component

MCP and skills55 Memory5 Guardrails and judges10 Monitors7 Permissions and sandboxing16 Fine-tuning and open weights3

Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 216papers have no tags yet and are not included in filtered results.

Attack surface / entry point：Tool and skill descriptions Attack surface / entry point：Weights and gradients Layer：Application layer Layer：Infrastructure layer Clear all

Another 216papers do not have category tags yet and are not included in filtered results.

AttacksarXiv 2610.12524Oct 8
An exploration of attacks on AI agent systems
Retest and extend prompt injection against AI agents, and use Agent Card deception to manipulate A2A selection
arXiv
2610.12524
Published
Oct 8
Layer
Application layer
Setting
AI Agent
Evaluated models
Ollama Mistral 0.9.5, llama3-8b-8192, gemini-2.0-flash-lite and others5
- AttacksPrompt injection
- TechniqueEncoding and obfuscation
- ComponentMCP and skills
AbstractSingle-agent filtering and classification can be bypassed by format or wording, and A2A card selection is also biased toward names and descriptions.
The authors retested prompt injection on their own LangChain, AutoGen, and A2A systems, and modified the Agent Card to see if choices shifted. The abstract states the experiments mainly highlight single-agent weaknesses while extending attacks to multi-agent.
Paper analysisRead analysis
AttacksarXiv 2610.10612Oct 7
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
Oct 7
Layer
Application layer
Setting
coding agent
Evaluated models
CISCO, HSS, AUDITOR and others8
- DefensesDetection and filtering
- AttacksDetection evasion
- TechniqueDefense-targeted
- ComponentMCP and skills
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
AttacksarXiv 2610.08098Oct 6
CORSA：面向技能路由器的技能注入攻击可跨路由器与 LLM 迁移
提出 CORSA，按任务簇优化技能注入的检索与执行
arXiv
2610.08098
Published
Oct 6
Layer
Application layer
Setting
coding agent
Evaluated models
GPT-5.4, DeepSeek-V4-Pro, Qwen3.8-27B and others5
- AttacksPoisoning and backdoors
- TechniqueSelection manipulation
- ComponentMCP and skills
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.07639Oct 6
HarnessSecurity-Bench horizontally evaluates the security mechanisms of six coding agent frameworks.
评测编码智能体 harness 安全机制在对抗任务中的防护效果
arXiv
2610.07639
Published
Oct 6
Layer
Application layer
Setting
coding agent
- AttacksPrompt injection
- ComponentPermissions and sandboxing
Paper analysisRead analysis
AttacksarXiv 2610.07510Oct 6
PersistBD: attackers can strengthen backdoors before release so that they maintain high attack success rates even after developer SFT and RL.
提出 PERSISTBD，发布前强化供应链后门使其经良性 SFT 与 RL 后仍外发凭据
arXiv
2610.07510
Published
Oct 6
Layer
Application layer
Setting
coding agent
Evaluated models
Qwen2.5-Coder-3B-Instruct, Qwen2.5-Coder-7B-Instruct, Qwen3-Coder-30B-A3B-Instruct
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentFine-tuning and open weights
Abstract总结了论文关于后门在 SFT/RL 中存活的发现、两因子机制、PERSISTBD 方法与核心数字。
本文研究第三方 LLM 智能体在开发者进行良性监督微调（SFT）和强化学习（RL）后训练时的后门持久性风险。
Paper analysisRead analysis
Analysis and theoryarXiv 2610.06001Oct 5
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
arXiv
2610.06001
Published
Oct 5
Layer
Application layer
Setting
coding agent
Evaluated models
gpt-5.6-terra, deepseek-v4-flash, glm-5.3-flash and others4
- DefensesDetection and filtering
- AttacksPoisoning and backdoors
- ComponentMCP and skills
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
AttacksarXiv 2610.05943Oct 5
CRIME 框架利用良性 Agent 技能组合诱发恶意行为
提出 CRIME 框架，组合良性 Agent 技能诱发恶意行为
arXiv
2610.05943
Published
Oct 5
Layer
Application layer
Setting
AI Agent
Evaluated models
DeepSeek-V4-Flash, GPT-4o-mini, GPT-4o and others6
- AttacksJailbreaks
- TechniqueAutomated search
- ComponentMCP and skills
Abstract良性技能经 DCA 或 ACA 组合后可产生恶意环境后果，单独审查对不上。
CRIME 把公共技能库中各自通过审查的技能配成两两组合，看联合执行能否实现指定恶意任务。。
Paper analysisRead analysis
DefensesarXiv 2610.05163Oct 4
Researchers construct segmented prompt injection on Claude Code and Codex and release a boundary action audit benchmark
提出 PAA 方法，在边界动作前审计长流程智能体的分阶段提示注入
arXiv
2610.05163
Published
Oct 4
Layer
Application layer
Setting
coding agent
Evaluated models
Claude Code (v2.1.172, Claude Sonnet 5), Codex CLI (v0.144.0, GPT-5.5)
- DefensesMonitoring and auditing
- AttacksPrompt injection
- ComponentMonitors
Abstract论文针对长流程注入提出边界动作审计与 PAA，在保持低误阻的同时实现高拦截率。
本研究针对长流程智能体在执行任务时面临的分阶段间接提示注入威胁，提出了在动作生效前进行拦截的边界动作审计框架与路径对齐归因方法。
Paper analysisRead analysis
DefensesarXiv 2610.06966Oct 4
APEX: proactively defending against indirect prompt injection at the LLM agent execution boundary.
提出 APEX，在执行边界用授权契约防御 Agent 间接提示注入
arXiv
2610.06966
Published
Oct 4
Layer
Application layer
Setting
AI Agent
Evaluated models
DeepSeek-V4-Flash, GLM-5.2, GPT-5.6-sol
- DefensesInstruction–data separation
- AttacksPrompt injection
- ComponentPermissions and sandboxing
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.04378Oct 3
COPEX：面向 MCP 智能体的受控攻击评测基准发布
提出 COPEX 基准，评测 MCP 智能体对多入口攻击的抵抗力
arXiv
2610.04378
Published
Oct 3
Layer
Application layer
Setting
AI Agent
Evaluated models
Claude Opus 4.7, Claude Sonnet 4.6, GPT-5.5 and others9
- AttacksPrompt injection
- ComponentMCP and skills
Paper analysisRead analysis
DefensesarXiv 2610.02861Oct 2
论文提出在 Kubernetes 上保护 AI Agent 的七层纵深防御框架与参考架构
提出 Kubernetes 运维智能体的七层纵深防御框架与参考架构
arXiv
2610.02861
Published
Oct 2
Layer
Application layer
Setting
AI Agent
- DefensesPermissions and approval
- AttacksPrompt injection
- ComponentPermissions and sandboxing
Abstract把运维智能体当不可信租户，用七层控制在完全攻破假设下约束行动。
把 Kubernetes 上的运维智能体当作不可信租户，在假定提示注入已完全控制其工具选择的前提下，用基础设施重建数据面与控制面的边界。要解决的是：智能体读日志、注解、工单或 MCP 工具描述时，这些内容可以变成它带着自身凭据执行的命令。模型对齐和分类器只降低概率。
Paper analysisRead analysis
DefensesarXiv 2610.02432Oct 2
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
Oct 2
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
- DefensesDetection and filtering
- AttacksDetection evasion
- ComponentGuardrails and judges
Paper analysisRead analysis
DefensesarXiv 2610.03089Oct 2
COBRA: A Dual-LLM Architecture for Defending Computer-Using Agents Against Branch-Jumping Attacks
提出 COBRA 双 LLM 架构，防御计算机使用 Agent 的分支转向攻击
arXiv
2610.03089
Published
Oct 2
Layer
Application layer
Setting
Browser and computer use
Evaluated models
gpt-5, UI-TARS-1.5-7B, claude-sonnet-5 and others6
- DefensesPermissions and approval
- AttacksPrompt injection
- ComponentPermissions and sandboxing
Abstract提出分支转向防御架构 COBRA，通过事前能力约束与边界代理消除分支转向攻击并兼顾效用。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.03153Oct 2
EvoRiskBench: An evolutionary benchmark for runtime security risks of workspace agents
构建 EvoRiskBench 评测工作区 Agent 的运行时安全风险
arXiv
2610.03153
Published
Oct 2
Layer
Application layer
Setting
AI Agent
Evaluated models
GPT-5.6 Sol, DeepSeek-V4-Pro-0813, Claude Opus 5
- AttacksPrompt injection
- ComponentMCP and skills
Abstract论文构建了工作空间智能体运行时风险基准 EvoRiskBench，发现高执行力智能体在 IPI 下面临较高安全风险。
Paper analysisRead analysis
AttacksarXiv 2610.01564Oct 1
APEX 用跨技能链劫持 LLM Agent
提出 APEX，用跨技能进度记录夹带虚假授权劫持 Agent
arXiv
2610.01564
Published
Oct 1
Layer
Application layer
Setting
AI Agent
Evaluated models
Claude Sonnet 5, DeepSeek V4 Flash, GPT-5.4 and others6
- AttacksPrompt injection
- TechniqueAutomated search
- ComponentMCP and skills
Paper analysisRead analysis
DefensesarXiv 2610.01349Oct 1
PACE：面向工具调用 LLM Agent 的来源感知能力强制执行
提出 PACE，在工具调用前做路径隔离与效果授权
arXiv
2610.01349
Published
Oct 1
Layer
Application layer
Setting
AI Agent
Evaluated models
gpt-5.6-luna, DeepSeek-V4-Flash, Qwen-3.8-27B
- DefensesInstruction–data separation
- AttacksPrompt injection
- ComponentPermissions and sandboxing
AbstractPACE 在工具边界做路径割与效果核验。
PACE 是面向工具调用型 LLM 智能体的运行时调解：当准入证据无法区分会改变行为的规格时，不在出口站点上撤销调解，而在最后一次工具调用前同时检查表示出的影响路径和请求权限。
Paper analysisRead analysis
AttacksarXiv 2609.39788Sep 30
研究：多智能体系统潜在通信链路可被训练用于提升有害顺从
提出只训练或篡改多智能体潜在通信链路来提高有害遵从
arXiv
2609.39788
Published
Sep 30
Layer
Application layer
Setting
Multi-agent systems
Evaluated models
Llama-3.2-3B-Instruct, Qwen2.5-3B-Instruct, Gemma-3-1B-IT and others7
- AttacksModel tampering
- TechniqueGradient and representation optimization
Abstract潜在链路本身即可改变冻结智能体系统的安全，奖励既能攻击也能修复。
学习得到的潜在通信链路会改变由冻结、对齐智能体组成的系统是否遵从有害请求。。作者研究三种拓扑：双智能体、三级顺序协作，以及双专家加汇总。
Paper analysisRead analysis
AttacksarXiv 2609.39607Sep 30
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
Sep 30
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)
- AttacksDetection evasion
- TechniqueAutomated search
- ComponentMCP and skills
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
DefensesarXiv 2609.39450Sep 30
ActionGuard：在工具调用执行前拦截被投毒技能
提出 ActionGuard 在执行前拦截被投毒技能诱发的未授权工具调用
arXiv
2609.39450
Published
Sep 30
Layer
Application layer
Setting
AI Agent
Evaluated models
Gemma 4 (gemma4:e4b-it-q4_K_M), Qwen 3.5 (qwen3.5:9b), Ministral 3 (ministral-3:8b-instruct-2512-q4_K_M) and others5
- DefensesInstruction–data separation
- AttacksPoisoning and backdoors
- ComponentMCP and skills
Paper analysisRead analysis
AttacksarXiv 2609.39352Sep 30
研究者提出解耦铺垫与执行的 LLM Agent 技能投毒攻击
提出 CoordPoison，解耦技能投毒的借口与动作
arXiv
2609.39352
Published
Sep 30
Layer
Application layer
Setting
coding agent
Evaluated models
DeepSeek-V4-Flash, GLM-5.3-Flash, Claude-Sonnet-4.6 and others5
- AttacksPoisoning and backdoors
- TechniqueAutomated search
- ComponentMCP and skills
AbstractCoordPoison 外置借口。
CoordPoison 是一种 Skill 供应链投毒方法，把“为何执行”和“执行什么”拆到两个 Skill。。
Paper analysisRead analysis

AI Safety Daily

Read the latest issueOne issue per day, updated as events develop

All papers

Attack type

Attack technique

Defense type

Impact

System type

Attacker access

Attack surface / entry point

Layer

System component

An exploration of attacks on AI agent systems

PyCache Trap 利用 Python 缓存替换绕过七款 Agent Skill 扫描器

CORSA：面向技能路由器的技能注入攻击可跨路由器与 LLM 迁移

HarnessSecurity-Bench horizontally evaluates the security mechanisms of six coding agent frameworks.

PersistBD: attackers can strengthen backdoors before release so that they maintain high attack success rates even after developer SFT and RL.

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

CRIME 框架利用良性 Agent 技能组合诱发恶意行为

Researchers construct segmented prompt injection on Claude Code and Codex and release a boundary action audit benchmark

APEX: proactively defending against indirect prompt injection at the LLM agent execution boundary.

COPEX：面向 MCP 智能体的受控攻击评测基准发布

论文提出在 Kubernetes 上保护 AI Agent 的七层纵深防御框架与参考架构

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

COBRA: A Dual-LLM Architecture for Defending Computer-Using Agents Against Branch-Jumping Attacks

EvoRiskBench: An evolutionary benchmark for runtime security risks of workspace agents

APEX 用跨技能链劫持 LLM Agent

PACE：面向工具调用 LLM Agent 的来源感知能力强制执行

研究：多智能体系统潜在通信链路可被训练用于提升有害顺从

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

ActionGuard：在工具调用执行前拦截被投毒技能

研究者提出解耦铺垫与执行的 LLM Agent 技能投毒攻击