DualView: Preventing Indirect Prompt Injection in Personal AI Agents | Paper Citation Record

Observation dca2c3c6-1186-4ef0-a358-88a3e2d19e33 · outbound

This paper cites React: Synergizing reasoning and acting in language models,.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents React: Synergizing reasoning and acting in language models,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3df4cbe-6537-4127-942f-ed0f89a3d12b · outbound

This paper cites Toolformer: Language models can teach themselves to use tools,.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents Toolformer: Language models can teach themselves to use tools,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 434c079f-6475-441c-a699-2cbe8987a82f · outbound

This paper cites Chatgpt plugins,.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents Chatgpt plugins,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa066d97-c493-496f-9d38-ce2f24e60067 · outbound

This paper cites What is microsoft 365 copilot?.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents What is microsoft 365 copilot?

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9879d03f-dc8f-4606-a15a-8b8f2f7c63f9 · outbound

This paper cites Model context protocol,.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents Model context protocol,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ead459a0-2ad3-4d4a-8e37-0cb00c4a2fde · outbound

This paper cites OpenClaw,.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents OpenClaw,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26126fcb-a15b-4847-83e1-def2d2878b26 · outbound

This paper cites Not what you’ve signed up for: Compromising real-world llm-integrated applications with indirect prompt injection,.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents Not what you’ve signed up for: Compromising real-world llm-integrated applications with indirect prompt injection,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d773cc28-72dc-49d7-ad30-e32eb3087cdf · outbound

This paper cites Formalizing and benchmarking prompt injection attacks and defenses,.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents Formalizing and benchmarking prompt injection attacks and defenses,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fff67a2c-b9bf-4c3f-bfd6-99c019a402a8 · outbound

This paper cites InjecAgent: Benchmarking indirect prompt injections in tool-integrated large language model agents,.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents InjecAgent: Benchmarking indirect prompt injections in tool-integrated large language model agents,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d91d6c0-f02f-4ed7-a99c-811fb6efcc2b · outbound

This paper cites The dual llm pattern for building ai assistants that can resist prompt injection,.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents The dual llm pattern for building ai assistants that can resist prompt injection,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb69f65f-e882-4682-a943-47ac5c597be1 · outbound

This paper cites Prompt Flow Integrity to Prevent Privilege Escalation in LLM Agents.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents Prompt Flow Integrity to Prevent Privilege Escalation in LLM Agents

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 285c5605-fad3-49bf-a22a-ee7a420b26e3 · outbound

This paper cites Defeating Prompt Injections by Design.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents Defeating Prompt Injections by Design

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ceaed338-de00-46f2-8064-13fc404bdf2f · outbound

This paper cites Securing AI Agents with Information-Flow Control.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents Securing AI Agents with Information-Flow Control

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b3d927d-6f33-4b1a-bc75-2ee3e65bea9c · outbound

This paper cites PinchBench,.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents PinchBench,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9de6ba4a-ebbc-4602-aaf6-104919081a38 · outbound

This paper cites Demystifying RCE vulnerabilities in LLM-integrated apps,.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents Demystifying RCE vulnerabilities in LLM-integrated apps,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6aca727-7578-49d2-9ab4-51ae5ef4f0f8 · outbound

This paper cites Agent security bench (ASB): Formalizing and benchmarking attacks and defenses in LLM-based agents,.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents Agent security bench (ASB): Formalizing and benchmarking attacks and defenses in LLM-based agents,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf24e6b1-21f0-4818-8fea-888e4bea5f7f · outbound

This paper cites AGENTVIGIL: Automatic black- box red-teaming for indirect prompt injection against LLM agents,.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents AGENTVIGIL: Automatic black- box red-teaming for indirect prompt injection against LLM agents,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 882da221-d8ed-4050-bd80-7898a459ec4b · outbound

This paper cites Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f174e6b4-bfa6-450a-9827-d0adc68dbdaa · outbound

This paper cites AgentDojo: A dynamic environment to evaluate prompt injection attacks and defenses for LLM agents,.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents AgentDojo: A dynamic environment to evaluate prompt injection attacks and defenses for LLM agents,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c95462f-3b54-482b-b0bc-636a2eca3ec3 · outbound

This paper cites Overcoming the retrieval barrier: Indirect prompt injection in the wild for LLM systems,.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents Overcoming the retrieval barrier: Indirect prompt injection in the wild for LLM systems,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e35e460-a5a2-4942-b7f3-4ca0e8c0aea4 · outbound

This paper cites ObliInjection: Order-oblivious prompt injection attack to LLM agents with multi-source data,.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents ObliInjection: Order-oblivious prompt injection attack to LLM agents with multi-source data,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 882e2567-952c-4882-928f-b03f29063928 · outbound

This paper cites Les dissonances: Cross-tool harvesting and polluting in pool-of-tools empowered LLM agents,.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents Les dissonances: Cross-tool harvesting and polluting in pool-of-tools empowered LLM agents,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b80a929-e222-4a6c-955f-7360eef6b3f3 · outbound

This paper cites Prompt injection attack to tool selection in LLM agents,.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents Prompt injection attack to tool selection in LLM agents,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b945dab-86de-41f1-96b2-ec684a6a57f4 · outbound

This paper cites Available: https://www.ndss-symposium.org/ndss- paper/prompt-injection-attack-to-tool-selection-in-llm-agents/.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents Available: https://www.ndss-symposium.org/ndss- paper/prompt-injection-attack-to-tool-selection-in-llm-agents/

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 707ad5aa-4db5-4f6b-b2c0-4196f9d91028 · outbound

This paper cites SpAIware: Uncovering a novel artificial intelligence attack vector through persistent memory in LLM applications and agents,.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents SpAIware: Uncovering a novel artificial intelligence attack vector through persistent memory in LLM applications and agents,

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae153de8-5f30-405f-820d-7432d7acf9c5 · outbound

This paper cites Memory injection attacks on LLM agents via query-only interaction,.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents Memory injection attacks on LLM agents via query-only interaction,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5e7cd97-a3b9-4f4a-81e2-0ecb909374ef · outbound

This paper cites Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems

Reference 28

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95266bf2-06bb-47ca-9c77-f4ae6bd75ff0 · outbound

This paper cites AirGapAgent: Protecting privacy-conscious conversational agents,.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents AirGapAgent: Protecting privacy-conscious conversational agents,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7fed1e6-e116-497d-bf6d-2365e4c49738 · outbound

This paper cites System-Level Defense against Indirect Prompt Injection Attacks: An Information Flow Control Perspective.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents System-Level Defense against Indirect Prompt Injection Attacks: An Information Flow Control Perspective

Reference 30

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c59a475-771f-49d2-810a-9549a5b4cd9f · outbound

This paper cites ACE: A security architecture for LLM-integrated app systems,.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents ACE: A security architecture for LLM-integrated app systems,

Reference 31

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c92e960b-82e4-47d8-80d9-bb68f10c45a3 · outbound

This paper cites Ignore Previous Prompt: Attack Techniques For Language Models.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents Ignore Previous Prompt: Attack Techniques For Language Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec6240b4-9108-4cff-a289-c1be0999ecda · outbound

This paper cites Jailbroken: How Does LLM Safety Training Fail?.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents Jailbroken: How Does LLM Safety Training Fail?

Reference 33

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c46affd-ac84-44db-9733-cc5622be7f73 · outbound

This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7249f692-e771-40e3-9be6-ae7690e9d25c · outbound

This paper cites The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions

Reference 35

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc8c9450-ca6d-4062-b6bc-fd841cec45ce · outbound

This paper cites StruQ: Defending Against Prompt Injection with Structured Queries.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents StruQ: Defending Against Prompt Injection with Structured Queries

Reference 36

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48306b39-cf50-4f26-a56f-c4788fb4604e · outbound

This paper cites SecAlign: Defending against prompt injection with preference optimization,.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents SecAlign: Defending against prompt injection with preference optimization,

Reference 37

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 618748e7-8306-4956-9a7c-a5ab2d650a3e · outbound

This paper cites Llama Prompt Guard 2,.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents Llama Prompt Guard 2,

Reference 38

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52445bad-392b-4d91-ba0f-481e686e6f3e · outbound

This paper cites LlamaFirewall: An open source guardrail system for building secure AI agents.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents LlamaFirewall: An open source guardrail system for building secure AI agents

Reference 39

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17091683-d763-4054-a35a-96ecbc467d19 · outbound

This paper cites DataSentinel: A game-theoretic detection of prompt injection attacks,.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents DataSentinel: A game-theoretic detection of prompt injection attacks,

Reference 40

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42c9e19f-6ee2-42ba-a3e7-7a02360d692e · outbound

This paper cites Defending Against Indirect Prompt Injection Attacks With Spotlighting.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents Defending Against Indirect Prompt Injection Attacks With Spotlighting

Reference 41

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd9e7f4e-d0a8-4f3d-8535-63d5d01ef2ca · outbound

This paper cites Attention is all you need to defend against indirect prompt injection attacks in LLMs,.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents Attention is all you need to defend against indirect prompt injection attacks in LLMs,

Reference 42

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa054f62-2795-4ad7-98c8-6a2a4f9a53cc · outbound

This paper cites MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents

Reference 43

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5a2d4c3-80de-4f1d-a254-4f1d356c252e · outbound

This paper cites The task shield: Enforcing task alignment to defend against indirect prompt injection in LLM agents,.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents The task shield: Enforcing task alignment to defend against indirect prompt injection in LLM agents,

Reference 44

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0a1c60e-41b9-4762-a575-6d9a2457a781 · outbound

This paper cites DRIFT: Dynamic rule-based defense with injection isolation for securing LLM agents,.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents DRIFT: Dynamic rule-based defense with injection isolation for securing LLM agents,

Reference 45

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 759734b3-9ed2-43c2-ac3d-c918a3d29ada · outbound

This paper cites ShieldAgent: Shielding agents via verifiable safety policy reasoning,.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents ShieldAgent: Shielding agents via verifiable safety policy reasoning,

Reference 46

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d20f98ca-a415-40ce-93d9-2e11d463a69f · outbound

This paper cites GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning

Reference 47

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dcbd94a6-d90b-4cb3-8eee-1c3c723c46bf · outbound

This paper cites AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents

Reference 48

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6fc5b00d-74af-4ecc-8d8f-5b149157070e · outbound

This paper cites RTBAS: Defending LLM Agents Against Prompt Injection and Privacy Leakage.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents RTBAS: Defending LLM Agents Against Prompt Injection and Privacy Leakage

Reference 49

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2041e5f4-7221-4875-b358-6eff8b6afffe · outbound

This paper cites Permissive information-flow analysis for large language models,.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents Permissive information-flow analysis for large language models,

Reference 50

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db07bc48-7ebe-4ebe-bc99-76253403e426 · outbound

This paper cites Optimization-based prompt injection attack to LLM-as-a-judge,.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents Optimization-based prompt injection attack to LLM-as-a-judge,

Reference 51

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59e95052-ea3e-4f48-9713-2a54f41b84dc · outbound

This paper cites OpenShell: A safe, private runtime for autonomous AI agents,.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents OpenShell: A safe, private runtime for autonomous AI agents,

Reference 52

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37419af9-99c8-45a0-be4c-ba9465a6fde7 · outbound

This paper cites Webhooks,.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents Webhooks,

Reference 53

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f781b8ee-0b2a-4233-ad64-777a60019a19 · outbound

This paper cites Configuration,.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents Configuration,

Reference 54

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c76b4449-a21d-4b33-b24d-1e9dcf3bcdc0 · outbound

This paper cites an unresolved cited work.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents Unresolved cited work

Reference 55

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7bb34070-789e-490d-8c82-77e285f646f2 · outbound

This paper cites gws: Google Workspace CLI,.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents gws: Google Workspace CLI,

Reference 56

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 040810cc-e61f-42db-a35a-2eb2519ed57b · outbound

This paper cites GitHub CLI,.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents GitHub CLI,

Reference 57

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c52f5f5f-d966-4c28-9e05-07c50195f8c3 · outbound

This paper cites Imprompter: Tricking LLM Agents into Improper Tool Use.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents Imprompter: Tricking LLM Agents into Improper Tool Use

Reference 58

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67683645-9ea2-4f0d-ba4b-14659bbfbac6 · outbound

This paper cites Great, now write an article about that: The crescendo multi-turn LLM jailbreak attack,.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents Great, now write an article about that: The crescendo multi-turn LLM jailbreak attack,

Reference 59

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f82c38fb-2c7f-4e1f-b78c-42d6d185762f · outbound

This paper cites PoisonedRAG: Knowledge corruption attacks to retrieval-augmented generation of large language models,.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents PoisonedRAG: Knowledge corruption attacks to retrieval-augmented generation of large language models,

Reference 60

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6bcc6d7-2155-4201-8c3c-759ac403c9b1 · outbound

This paper cites IsolateGPT: An Execution Isolation Architecture for LLM-Based Agentic Systems.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents IsolateGPT: An Execution Isolation Architecture for LLM-Based Agentic Systems

Reference 61

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f082d9f9-40a2-4a0a-86e3-7febf098484c · outbound

This paper cites Optimizing agent planning for security and autonomy,.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents Optimizing agent planning for security and autonomy,

Reference 62

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a214d93e-87bd-495f-ac05-416f1694e95b · outbound

This paper cites Progent: Securing AI Agents with Privilege Control.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents Progent: Securing AI Agents with Privilege Control

Reference 63

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b31e0bc6-77f8-4d07-a83e-586c8767cefd · outbound

This paper cites Contextual Agent Security: A Policy for Every Purpose.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents Contextual Agent Security: A Policy for Every Purpose

Reference 64

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1092bb99-0554-414c-88d7-2399c63618c8 · outbound

This paper cites SAGA: A security architecture for governing AI agentic systems,.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents SAGA: A security architecture for governing AI agentic systems,

Reference 65

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf914bd3-be8f-489b-9fce-d95e06632c34 · outbound

This paper cites Claude Code hooks reference,.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents Claude Code hooks reference,

Reference 66

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cabf711b-7a39-40a9-87f7-6d5411bce605 · outbound

This paper cites Hermes Agent: Hooks,.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents Hermes Agent: Hooks,

Reference 67

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66a8c0fe-fb11-487b-a116-ba50bb894277 · outbound

This paper cites Make agent defeat agent: Automatic detection of Taint-Style vulnerabilities in LLM-based agents,.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents Make agent defeat agent: Automatic detection of Taint-Style vulnerabilities in LLM-based agents,

Reference 68

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0779c28-2aac-4ee1-9332-1943b60d6d4e · outbound

This paper cites Quarterly report.

DualView: Preventing Indirect Prompt Injection in Personal AI Agents Quarterly report

Reference 69

Resolution: unresolved; no resolver link, observed 2026-07-11T23:43:28.649948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers