Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-07T11:59:29.316286Z
Paper Citation Record · LEDGER
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution
As of 7 August 2026, this Paper Citation Record lists 67 of 67 outbound references and 15 inbound Pith citation observations for arXiv:2506.01055.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-06T23:42:13.675310Z
A source-named dated measurement, never combined with another source.
Source: arxiv_reference, observed 2026-07-04T14:09:53.274632Z
Reference resolution
67 of 67 outbound references displayed
- verified exact0
- verified fuzzy22
- unresolved42
- parse uncertain0
- malformed identifier1
- metadata mismatch2
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation b6f0e221-2d9a-4368-8ab0-b1c6d767829f · outbound
This paper cites Design and analysis of experiments in anfis modeling for stock price prediction.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Design and analysis of experiments in anfis modeling for stock price prediction
Reference 1
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T11:59:35.628259Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 7a4c949a-cbd9-440b-9e43-79600e8dddd4 · outbound
This paper cites Tokenization of social media engagements increases the sharing of false (and other) news but penalization moderates it.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Tokenization of social media engagements increases the sharing of false (and other) news but penalization moderates it
Reference 2
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:59:21.335328Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 75465aea-4feb-4922-a429-4fb572be487b · outbound
This paper cites Open-source llms for text annotation: a practical guide for model setting and fine-tuning.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Open-source llms for text annotation: a practical guide for model setting and fine-tuning
Reference 3
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T11:59:35.519043Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation ac80c41a-574f-4aba-be29-e168c9314393 · outbound
This paper cites Extracting training data from large language models.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Extracting training data from large language models
Reference 4
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:59:21.573012Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7f7de28f-a88e-4d14-8718-07fb20684ef6 · outbound
This paper cites PLACES: Prompting Language Models for Social Conversation Synthesis.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution PLACES: Prompting Language Models for Social Conversation Synthesis
Reference 5
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:59:21.745391Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 09fdaad2-4160-442b-b84e-2d0dc3a1298b · outbound
This paper cites SecAlign: Defending Against Prompt Injection with Preference Optimization.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution SecAlign: Defending Against Prompt Injection with Preference Optimization
Reference 7
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:59:22.064371Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0ef5d5c0-322e-413f-929a-8bc01c3453e3 · outbound
This paper cites Dataset and lessons learned from the 2024 satml llm capture-the-flag competition.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Dataset and lessons learned from the 2024 satml llm capture-the-flag competition
Reference 8
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T11:59:35.392317Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 49bf43cb-85b5-43f4-a420-06bc98ea5ef4 · outbound
This paper cites AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
Reference 9
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:59:22.378791Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation deeac7ee-acaf-4159-b823-e10d8873ca34 · outbound
This paper cites Defeating Prompt Injections by Design.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Defeating Prompt Injections by Design
Reference 10
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:59:22.444702Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1e72cc58-0342-479f-a86a-302e60b424ef · outbound
This paper cites How we estimate the risk from prompt injection attacks on ai systems, 2025.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution How we estimate the risk from prompt injection attacks on ai systems, 2025
Reference 11
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T11:59:35.247820Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 662f2b23-c9d8-4462-b276-496aa0e30648 · outbound
This paper cites AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback
Reference 12
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:59:22.616939Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation dd3e2ab9-fa09-4007-bd66-221aa369694f · outbound
This paper cites Scaling Synthetic Data Creation with 1,000,000,000 Personas.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Scaling Synthetic Data Creation with 1,000,000,000 Personas
Reference 13
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:59:22.698654Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4ded8383-d074-4575-aabe-ffb595d743d3 · outbound
This paper cites A utility theory approach for insurance pricing.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution A utility theory approach for insurance pricing
Reference 14
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T11:59:35.103451Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation c2d74b0e-2cfc-490e-b576-61cb250bd370 · outbound
This paper cites ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks
Reference 15
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:59:22.843126Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5e2a9241-9f69-4f69-9418-922b1a95b62f · outbound
This paper cites Not what you’ve signed up for: Compromising real-world llm-integrated applications with indirect prompt injection.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Not what you’ve signed up for: Compromising real-world llm-integrated applications with indirect prompt injection
Reference 16
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:59:22.928822Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 78a771e9-8386-421e-8d6c-f61e52efb794 · outbound
This paper cites Which Economic Tasks are Performed with AI? Evidence from Millions of Claude Conversations.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Which Economic Tasks are Performed with AI? Evidence from Millions of Claude Conversations
Reference 17
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:59:22.997850Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 613ad52f-e909-4670-8cbc-073760966e52 · outbound
This paper cites Defending Against Indirect Prompt Injection Attacks With Spotlighting.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Defending Against Indirect Prompt Injection Attacks With Spotlighting
Reference 18
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:59:23.059071Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9949848e-882c-4c87-ae21-d591081d1305 · outbound
This paper cites Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
Reference 19
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:59:23.191027Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 23f2973f-7c34-4911-8a75-4fa125bc1782 · outbound
This paper cites AI Agents That Matter.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution AI Agents That Matter
Reference 21
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:59:23.446266Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1c312d15-7b96-4800-a0e9-9e46a94bd7ae · outbound
This paper cites Characterizing AI Agents for Alignment and Governance.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Characterizing AI Agents for Alignment and Governance
Reference 22
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:59:23.583657Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6fdef1ce-fe9b-42b6-b902-99a5c0e044b2 · outbound
This paper cites Language models can solve computer tasks.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Language models can solve computer tasks
Reference 23
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:59:23.717002Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation caa68dbd-0276-4969-956e-41af70eff051 · outbound
This paper cites SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualization.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualization
Reference 24
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:59:23.855159Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ef89007e-f328-4f9e-8689-13cf50d49c73 · outbound
This paper cites Propile: Probing privacy leakage in large language models.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Propile: Probing privacy leakage in large language models
Reference 25
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:59:23.991411Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a8f0f3a0-1322-4cf0-b652-1c50498600d5 · outbound
This paper cites RESI: An R Package for Robust Effect Sizes.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution RESI: An R Package for Robust Effect Sizes
Reference 26
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:59:24.120956Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d03f9618-b552-4669-b094-2e714319e407 · outbound
This paper cites Formalizing and benchmarking prompt injection attacks and defenses.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Formalizing and benchmarking prompt injection attacks and defenses
Reference 27
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:59:24.271893Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8f83a0ad-064f-46f8-af01-0f90539c79b4 · outbound
This paper cites A holistic approach to undesired content detection in the real world.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution A holistic approach to undesired content detection in the real world
Reference 28
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T11:59:34.968300Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation c6fe0fe6-b375-490a-a5dd-8d03ea867460 · outbound
This paper cites The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey
Reference 29
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:59:24.591514Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 25ac0349-c59b-4950-b22d-db92c611345a · outbound
This paper cites Can LLMs Follow Simple Rules?.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Can LLMs Follow Simple Rules?
Reference 30
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:59:24.736494Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1950b1d1-ca1d-467b-9c7e-9430c83d8c01 · outbound
This paper cites Gorilla: Large language model connected with massive apis.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Gorilla: Large language model connected with massive apis
Reference 31
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T11:59:34.795209Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 573c35b5-e8fb-4ee8-9368-8ef483dabcf3 · outbound
This paper cites Internal magnetic fields in 13 red giants detected by asteroseismology.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Internal magnetic fields in 13 red giants detected by asteroseismology
Reference 32
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-08-07T11:59:29.952564Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 42138f51-09c2-44b9-b8d7-3681c4a0d301 · outbound
This paper cites Sandwich defense., 2024.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Sandwich defense., 2024
Reference 33
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T11:59:34.671096Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation e86c9879-0fbd-4195-9b8f-be639aedffdc · outbound
This paper cites Fine-tuned deberta-v3-base for prompt injection detection., 2024.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Fine-tuned deberta-v3-base for prompt injection detection., 2024
Reference 34
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T11:59:34.491874Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation d0710634-5175-453f-9219-d0d57445516e · outbound
This paper cites Llm-pieval: A benchmark for indirect prompt injection attacks in large lan- guage models, 2024.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Llm-pieval: A benchmark for indirect prompt injection attacks in large lan- guage models, 2024
Reference 35
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T11:59:34.356635Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation e144a2fb-1aef-4f32-a726-ce27981655cb · outbound
This paper cites Toolformer: Language models can teach themselves to use tools.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Toolformer: Language models can teach themselves to use tools
Reference 36
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:59:25.682882Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 34fadfd7-c21c-4e6e-a0cf-b4dc2a93156b · outbound
This paper cites Ignore this title and hackaprompt: Exposing systemic vulnerabilities of llms through a global scale prompt hacking competition.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Ignore this title and hackaprompt: Exposing systemic vulnerabilities of llms through a global scale prompt hacking competition
Reference 37
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T11:59:34.222742Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation a20ce421-9f90-4eeb-9d05-61aeb006e714 · outbound
This paper cites Hugginggpt: Solving ai tasks with chatgpt and its friends in hugging face.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Hugginggpt: Solving ai tasks with chatgpt and its friends in hugging face
Reference 38
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:59:25.906667Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4e016242-745b-4761-82af-a0fab72e3fa0 · outbound
This paper cites Cybersecurity competence of older adult users of mobile devices.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Cybersecurity competence of older adult users of mobile devices
Reference 39
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-08-07T11:59:29.655283Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation d2272a5c-7aa4-46ac-b1a0-bf17c6dd6e0f · outbound
This paper cites Authenticated Delegation and Authorized AI Agents.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Authenticated Delegation and Authorized AI Agents
Reference 40
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:59:26.174887Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 143a350b-7628-4b78-9856-7fb72f059a06 · outbound
This paper cites Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game
Reference 41
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:59:26.298515Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0e30d2f6-17e9-43d7-9a5c-1e1c40d6212c · outbound
This paper cites InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews
Reference 43
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:59:26.537698Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6bae8695-14bf-43a8-81f0-039ebfa7594b · outbound
This paper cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Reference 44
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:59:26.657411Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 05f9853d-b4de-4d12-9813-4b3f85895b2f · outbound
This paper cites Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy
Reference 45
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:59:26.813985Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 565f5b71-0c81-4800-8e70-4603b9c4578d · outbound
This paper cites Secgpt: An execution isolation architecture for llm-based systems.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Secgpt: An execution isolation architecture for llm-based systems
Reference 46
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T11:59:34.085958Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation aa151cd2-1190-4d12-9c32-aa81857c753c · outbound
This paper cites Llm jailbreak attack versus defense techniques–a comprehensive study.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Llm jailbreak attack versus defense techniques–a comprehensive study
Reference 47
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T11:59:33.966976Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 93041c29-21c3-4a4d-acbe-f32c5f9b8e18 · outbound
This paper cites InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents
Reference 48
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:59:27.193670Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation eee90784-3012-4dab-b276-ffd02253c17c · outbound
This paper cites Benchmarking large language models for news summarization.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Benchmarking large language models for news summarization
Reference 49
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:59:27.351580Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d1a3eb34-1cae-49ac-a1e5-9a5996482d17 · outbound
This paper cites RTBAS: Defending LLM Agents Against Prompt Injection and Privacy Leakage.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution RTBAS: Defending LLM Agents Against Prompt Injection and Privacy Leakage
Reference 50
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:59:27.473122Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9d047759-7136-4d82-b9c5-d8783005a7b8 · outbound
This paper cites Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis
Reference 51
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:59:27.585284Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5b45135c-ddb1-4e8a-b391-525950ef0baf · outbound
This paper cites Adversarial prompting techniques for llms.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Adversarial prompting techniques for llms
Reference 52
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T11:59:33.817890Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 9931e2ed-3a9e-4a01-b986-f997ec53af2a · outbound
This paper cites Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?
Reference 53
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:59:27.808634Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ffb64630-b86f-4537-99c5-4f30add2e422 · outbound
This paper cites an unresolved cited work.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Unresolved cited work
Reference 54
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T11:59:33.652069Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 3630f469-ab2f-4495-84c5-a3f5d1089075 · outbound
This paper cites an unresolved cited work.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Unresolved cited work
Reference 55
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T11:59:33.521309Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation a403d442-fd1b-443f-8b1a-6110339d06b0 · outbound
This paper cites Guidelines:.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Guidelines:
Reference 56
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T11:59:33.370288Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 74446354-f9c1-4f05-bf39-036dfd75f5a5 · outbound
This paper cites All results are based on AgentDojo which has a Github repository including codes and data.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution All results are based on AgentDojo which has a Github repository including codes and data
Reference 57
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T11:59:33.213087Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 6289da26-c633-409e-9013-55694a5ff888 · outbound
This paper cites We will release our new synthetic dataset upon acceptance of the paper.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution We will release our new synthetic dataset upon acceptance of the paper
Reference 58
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T11:59:33.054961Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 1255966c-6783-4944-947a-720a3d0f5208 · outbound
This paper cites an unresolved cited work.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Unresolved cited work
Reference 59
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T11:59:32.891590Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 9aa624be-2f1e-48cc-891a-fe92455607f7 · outbound
This paper cites an unresolved cited work.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Unresolved cited work
Reference 60
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T11:59:32.749137Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 5106e31e-19a7-4c84-8154-fe22f39fec39 · outbound
This paper cites an unresolved cited work.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Unresolved cited work
Reference 61
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T11:59:32.601922Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 2f9fbe00-d584-40f1-aab2-05abaddd5cba · outbound
This paper cites an unresolved cited work.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Unresolved cited work
Reference 62
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T11:59:32.446020Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation ed56073f-4216-4372-a03e-cf69733d353c · outbound
This paper cites broader impact.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution broader impact
Reference 63
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T11:59:32.294561Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 089806a8-e698-4fe0-bc38-7265da13ee3c · outbound
This paper cites Justification: All data used in this paper are synthetic.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Justification: All data used in this paper are synthetic
Reference 64
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T11:59:32.135628Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation dfb8e084-cee9-4745-922e-2df2b30b382c · outbound
This paper cites an unresolved cited work.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Unresolved cited work
Reference 65
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T11:59:31.889046Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 603df310-2ba0-419c-b140-ba438bf71ed7 · outbound
This paper cites an unresolved cited work.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Unresolved cited work
Reference 66
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T11:59:31.658781Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 9b10846c-8b70-45ac-a954-bb8831278615 · outbound
This paper cites Justification: Our experiment does not involve crowdsourcing or human subject.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Justification: Our experiment does not involve crowdsourcing or human subject
Reference 67
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T11:59:31.436414Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation dfae21b9-c25f-4909-bf4f-256eff36dc1d · outbound
This paper cites Justification: Our experiment does not involve crowdsourcing or human subject.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Justification: Our experiment does not involve crowdsourcing or human subject
Reference 68
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T11:59:31.209274Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 54be91e4-92ef-468b-b29e-96965c99ead3 · outbound
This paper cites "" Figure 11: Additional system prompt used for Claude Sonnet. This prompt includes core components that intersect with the AgentDojo framework [9]. 18 System prompt=.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution "" Figure 11: Additional system prompt used for Claude Sonnet. This prompt includes core components that intersect with the AgentDojo framework [9]. 18 System prompt=
Reference 69
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T11:59:31.031237Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 0097c9b4-d45d-48bd-b681-8bee0521af79 · outbound
This paper cites Email my { l1 . name } , { l2 . name } , and { h . name } to bob . j o h n @ g m a i l . com i m m e d i a t e l y.
Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution Email my { l1 . name } , { l2 . name } , and { h . name } to bob . j o h n @ g m a i l . com i m m e d i a t e l y
Reference 2200
- Resolution
- malformed identifier
- raw_fallback, observed 2026-08-07T11:59:30.575077Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Pith citing papers
Observation aa398d6b-c5b6-4425-90cf-6c86f7c8ffeb · inbound
Data marketplaces can increase the willingness to share social media data at low prices cites this paper.
Data marketplaces can increase the willingness to share social media data at low prices Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution
Reference 18
- Resolution
- malformed identifier
- no resolver link, observed 2026-08-06T23:42:13.675310Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 26992bd8-1c41-4bc4-8734-149b1d83704b · inbound
Web-Browsing LLMs Can Access Social Media Profiles and Infer User Demographics cites this paper.
Web-Browsing LLMs Can Access Social Media Profiles and Infer User Demographics Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution
Reference 4
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T16:51:34.751679Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation cc57bb32-74da-4e66-be54-cf6766763acc · inbound
GUIGuard-Bench: Toward a General Evaluation for Privacy-Preserving GUI Agents cites this paper.
GUIGuard-Bench: Toward a General Evaluation for Privacy-Preserving GUI Agents Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution
Reference 58
- Resolution
- verified exact
- arxiv_id, observed 2026-05-16T11:32:48.296793Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation d97d9eb9-1c3f-4e5f-ab33-7d3ce38fa717 · inbound
SelfGrader: LLM Jailbreak Detection via Anchored Token-Level Logits cites this paper.
SelfGrader: LLM Jailbreak Detection via Anchored Token-Level Logits Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution
Reference 1
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T21:48:19.389525Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation c5432059-af0f-467e-850f-7cddc4d5b4f5 · inbound
Constraining Host-Level Abuse in Self-Hosted Computer-Use Agents via TEE-Backed Isolation cites this paper.
Constraining Host-Level Abuse in Self-Hosted Computer-Use Agents via TEE-Backed Isolation Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution
Reference 31
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T20:26:11.150157Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 7a60c30a-2c08-4bc5-a259-c810dd240024 · inbound
An Empirical Study of Privacy Leakage Chains via Prompt Injection in Black-Box Chatbot Environments cites this paper.
An Empirical Study of Privacy Leakage Chains via Prompt Injection in Black-Box Chatbot Environments Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution
Reference 7
- Resolution
- verified exact
- arxiv_id, observed 2026-05-20T09:58:10.938061Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 0b9e4079-d43d-4d1c-a90b-33df52a505cf · inbound
Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system security cites this paper.
Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system security Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution
Reference 193
- Resolution
- verified exact
- arxiv_id, observed 2026-06-30T19:45:01.603801Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation efa56cf7-2bed-4683-82d3-68d0041a9f7d · inbound
Security of OpenClaw Agents: Fundamentals, Attacks, and Countermeasures cites this paper.
Security of OpenClaw Agents: Fundamentals, Attacks, and Countermeasures Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution
Reference 34
- Resolution
- verified exact
- arxiv_id, observed 2026-06-29T22:04:00.356123Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation c474a8d3-7ade-495c-b12b-2f44d2d66a25 · inbound
When AI Meets Wall Street: A Survey on Trustworthy AI in Fintech cites this paper.
When AI Meets Wall Street: A Survey on Trustworthy AI in Fintech Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution
Reference 6
- Resolution
- verified exact
- arxiv_id, observed 2026-06-29T14:43:31.588391Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 45f88d7a-7e50-49fa-923e-5f9c34979c4b · inbound
SeClaw: Spec-Driven Security Task Synthesis for Evaluating Autonomous Agents cites this paper.
SeClaw: Spec-Driven Security Task Synthesis for Evaluating Autonomous Agents Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution
Reference 1
- Resolution
- verified exact
- arxiv_id, observed 2026-07-01T23:56:23.009280Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 99079ee5-69d8-4355-859d-8d3dd859423b · inbound
CAPED: Context-Aware Privacy Exposure Defense for Mobile GUI Agents cites this paper.
CAPED: Context-Aware Privacy Exposure Defense for Mobile GUI Agents Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution
Reference 37
- Resolution
- verified exact
- arxiv_id, observed 2026-07-03T12:28:07.466005Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 5649493c-6fb9-4c0a-99c3-fd1d0f6f4ac0 · inbound
Who Pays the Price? Stakeholder-Centric Prompt Injection Benchmarking for Real-world Web Agents cites this paper.
Who Pays the Price? Stakeholder-Centric Prompt Injection Benchmarking for Real-world Web Agents Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution
Reference 14
- Resolution
- verified exact
- arxiv_id, observed 2026-07-03T15:48:35.889462Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation a07f2713-7cc3-4a53-baa4-4933295abb7b · inbound
TRAP: Benchmark for Task-completion and Resistance to Active Privacy-extraction cites this paper.
TRAP: Benchmark for Task-completion and Resistance to Active Privacy-extraction Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution
Reference 2
- Resolution
- verified exact
- arxiv_id, observed 2026-07-04T01:09:19.371396Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 30396437-70b1-4906-a799-c6cccba169b2 · inbound
GIF: Locally Sound Geometric Information Flow Control for LLMs cites this paper.
GIF: Locally Sound Geometric Information Flow Control for LLMs Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution
Reference 4
- Resolution
- verified exact
- arxiv_id, observed 2026-07-04T10:49:46.729444Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 4a66fa44-d82b-47e4-82bf-e5b1d61d962f · inbound
Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents cites this paper.
Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution
Reference 4
- Resolution
- verified exact
- arxiv_id, observed 2026-07-04T14:09:53.276106Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.