Paper Citation Record · LEDGER

Agent Data Injection Attacks are Realistic Threats to AI Agents

As of 17 August 2026, this Paper Citation Record lists 65 of 65 outbound references and 1 inbound Pith citation observation for arXiv:2607.05120.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2607.05120 v1

Coverage vector

measured 65 of 65 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-11T08:31:36.099368Z

measured 66 of 66 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T21:47:02.723794Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

65 of 65 outbound references displayed

verified exact0
verified fuzzy0
unresolved65
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation b2ad5205-633a-4304-bb06-898f0114687d · outbound

This paper cites Chatgpt,.

Agent Data Injection Attacks are Realistic Threats to AI Agents Chatgpt,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3cdf4264-41b7-4ea4-9348-9ff7faea68bd · outbound

This paper cites Claude in chrome,.

Agent Data Injection Attacks are Realistic Threats to AI Agents Claude in chrome,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 351f3568-13be-46d0-9267-a3953b926509 · outbound

This paper cites Google gemini cli,.

Agent Data Injection Attacks are Realistic Threats to AI Agents Google gemini cli,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97975772-6001-48e1-aec3-0a914974cfd0 · outbound

This paper cites Cross-site scripting (xss) attacks and defense mechanisms: classification and state-of-the-art,.

Agent Data Injection Attacks are Realistic Threats to AI Agents Cross-site scripting (xss) attacks and defense mechanisms: classification and state-of-the-art,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b2be458-3acd-469b-948c-d00a4ccd3913 · outbound

This paper cites Clarke-Salt,SQL injection attacks and defense.

Agent Data Injection Attacks are Realistic Threats to AI Agents Clarke-Salt,SQL injection attacks and defense

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c077783f-db76-4093-989d-96dd4aedb0e2 · outbound

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

Agent Data Injection Attacks are Realistic Threats to AI Agents Not what you’ve signed up for: Compromising real- world llm-integrated applications with indirect prompt injection,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d60a3ead-99eb-4f53-8a86-f018ab8c7572 · outbound

This paper cites Prompt Injection attack against LLM-integrated Applications.

Agent Data Injection Attacks are Realistic Threats to AI Agents Prompt Injection attack against LLM-integrated Applications

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa3314d3-c3fa-4027-98e2-0b3b8e754aea · outbound

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

Agent Data Injection Attacks are Realistic Threats to AI Agents Imprompter: Tricking LLM Agents into Improper Tool Use

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff8b731a-f784-41bb-8327-b93aea98fd3d · outbound

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

Agent Data Injection Attacks are Realistic Threats to AI Agents The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9710b8c7-0f4b-4c32-b81c-2e2c3e4bf1d3 · outbound

This paper cites {StruQ}: Defending against prompt injection with structured queries,.

Agent Data Injection Attacks are Realistic Threats to AI Agents {StruQ}: Defending against prompt injection with structured queries,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f334b0a3-0707-4504-abdb-fe7d55d084ba · outbound

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

Agent Data Injection Attacks are Realistic Threats to AI Agents Datasentinel: A game-theoretic detection of prompt injection attacks,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98bac509-7806-4ad5-b02d-770b779a9707 · outbound

This paper cites PromptArmor: Simple yet Effective Prompt Injection Defenses.

Agent Data Injection Attacks are Realistic Threats to AI Agents PromptArmor: Simple yet Effective Prompt Injection Defenses

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c00bd23e-3b1f-4081-9750-42e7b28dca22 · outbound

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

Agent Data Injection Attacks are Realistic Threats to AI Agents Prompt Flow Integrity to Prevent Privilege Escalation in LLM Agents

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06284f71-e3be-4aa2-9643-7498b27d9bc9 · outbound

This paper cites Defeating Prompt Injections by Design.

Agent Data Injection Attacks are Realistic Threats to AI Agents Defeating Prompt Injections by Design

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79aa6edc-c976-400b-95cf-2ad149ccc101 · outbound

This paper cites Claude code,.

Agent Data Injection Attacks are Realistic Threats to AI Agents Claude code,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f9f1c59-cfea-4e3a-baf4-6c49d1628fd8 · outbound

This paper cites an unresolved cited work.

Agent Data Injection Attacks are Realistic Threats to AI Agents Unresolved cited work

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5114a6ac-373b-4460-8ba8-a003bc0c0ba8 · outbound

This paper cites Google antigravity,.

Agent Data Injection Attacks are Realistic Threats to AI Agents Google antigravity,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a662b706-24e1-4cbf-a36c-3a54aacdad25 · outbound

This paper cites Nanobrowser - open source ai web agent,.

Agent Data Injection Attacks are Realistic Threats to AI Agents Nanobrowser - open source ai web agent,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e6da0e5-bd43-4186-8371-a632b58d4a29 · outbound

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

Agent Data Injection Attacks are Realistic Threats to AI Agents Agentdojo: A dynamic environment to evaluate prompt injection attacks and defenses for LLM agents,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8755bb9-9c53-4372-9750-e82163526e73 · outbound

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

Agent Data Injection Attacks are Realistic Threats to AI Agents Toolformer: Language models can teach themselves to use tools,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8d8b969-6124-4a8c-b340-7c065e00981f · outbound

This paper cites an unresolved cited work.

Agent Data Injection Attacks are Realistic Threats to AI Agents Unresolved cited work

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c0522da-0bf0-4a5e-91e8-2fc657b05cae · outbound

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

Agent Data Injection Attacks are Realistic Threats to AI Agents Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e7a3ec7-f6c3-4933-8cff-e1b0af2da59d · outbound

This paper cites Eia: Environmental injection attack on generalist web agents for privacy leakage,.

Agent Data Injection Attacks are Realistic Threats to AI Agents Eia: Environmental injection attack on generalist web agents for privacy leakage,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c500a932-bbf8-43ef-9566-fcbf7d81dba0 · outbound

This paper cites Agentvigil: Generic black-box red-teaming for indirect prompt injection against llm agents,.

Agent Data Injection Attacks are Realistic Threats to AI Agents Agentvigil: Generic black-box red-teaming for indirect prompt injection against llm agents,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78859368-5870-4106-b258-08ffdc69049c · outbound

This paper cites Dissecting adversarial robustness of multimodal lm agents,.

Agent Data Injection Attacks are Realistic Threats to AI Agents Dissecting adversarial robustness of multimodal lm agents,

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fee6ffa-4277-4d24-943c-19a1240eda4e · outbound

This paper cites Data execution prevention,.

Agent Data Injection Attacks are Realistic Threats to AI Agents Data execution prevention,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f837cff-9e22-448a-9604-2bcf81afed4c · outbound

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

Agent Data Injection Attacks are Realistic Threats to AI Agents Formalizing and benchmarking prompt injection attacks and defenses,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2bddc5c5-00cb-4240-8c74-b0a1bac283e8 · outbound

This paper cites Delimiters won’t save you from prompt injection,.

Agent Data Injection Attacks are Realistic Threats to AI Agents Delimiters won’t save you from prompt injection,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef129ad2-b293-43bf-9f7c-a35baf8c6c3e · outbound

This paper cites Invitation Is All You Need! Promptware Attacks Against LLM-Powered Assistants in Production Are Practical and Dangerous.

Agent Data Injection Attacks are Realistic Threats to AI Agents Invitation Is All You Need! Promptware Attacks Against LLM-Powered Assistants in Production Are Practical and Dangerous

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92a8f9da-1d35-44ad-b36a-a5ac21848e4d · outbound

This paper cites Chatgpt atlas,.

Agent Data Injection Attacks are Realistic Threats to AI Agents Chatgpt atlas,

Reference 30

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31ebb0e0-1170-4d19-a53a-04238dd915f7 · outbound

This paper cites Pytorch: An imperative style, high-performance deep learning library,.

Agent Data Injection Attacks are Realistic Threats to AI Agents Pytorch: An imperative style, high-performance deep learning library,

Reference 31

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87286852-4156-48ac-803e-41264a591113 · outbound

This paper cites {TensorFlow}: a system for {Large-Scale} machine learning,.

Agent Data Injection Attacks are Realistic Threats to AI Agents {TensorFlow}: a system for {Large-Scale} machine learning,

Reference 32

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ce2515c-9779-466d-bebe-c2fa8720e388 · outbound

This paper cites Github cli,.

Agent Data Injection Attacks are Realistic Threats to AI Agents Github cli,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76d6bedb-24c4-41dc-b409-4e2bd9f4d459 · outbound

This paper cites Github mcp server,.

Agent Data Injection Attacks are Realistic Threats to AI Agents Github mcp server,

Reference 34

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d60d25a4-17a4-4dc0-9138-abd2ae1e2de6 · outbound

This paper cites Keeping llms aligned after fine-tuning: The crucial role of prompt templates,.

Agent Data Injection Attacks are Realistic Threats to AI Agents Keeping llms aligned after fine-tuning: The crucial role of prompt templates,

Reference 35

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3188ae9-53d7-42bf-b598-c3578230d089 · outbound

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

Agent Data Injection Attacks are Realistic Threats to AI Agents LlamaFirewall: An open source guardrail system for building secure AI agents

Reference 36

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9eb4f866-d0b6-498b-bfa0-d98b81f35732 · outbound

This paper cites Design Patterns for Securing LLM Agents against Prompt Injections.

Agent Data Injection Attacks are Realistic Threats to AI Agents Design Patterns for Securing LLM Agents against Prompt Injections

Reference 37

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0528cdd3-554e-4a5d-a767-ace6916c8319 · outbound

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

Agent Data Injection Attacks are Realistic Threats to AI Agents IsolateGPT: An Execution Isolation Architecture for LLM-Based Agentic Systems,

Reference 38

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0735d94d-5e06-4a47-831e-1591fd8354c2 · outbound

This paper cites ACE: A Security Architecture for LLM-Integrated App Systems.

Agent Data Injection Attacks are Realistic Threats to AI Agents ACE: A Security Architecture for LLM-Integrated App Systems

Reference 39

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5dd1713b-be86-47b1-9b78-f801b4b96b6d · outbound

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

Agent Data Injection Attacks are Realistic Threats to AI Agents Progent: Securing AI Agents with Privilege Control

Reference 40

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a059039-8f7b-4ab3-b758-2b3dd2bcdabf · outbound

This paper cites Contextual agent security: A policy for every purpose,.

Agent Data Injection Attacks are Realistic Threats to AI Agents Contextual agent security: A policy for every purpose,

Reference 41

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6c6e136-9b37-4948-82df-e6098eaf48e9 · outbound

This paper cites Towards automating data access permissions in ai agents,.

Agent Data Injection Attacks are Realistic Threats to AI Agents Towards automating data access permissions in ai agents,

Reference 42

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51b73398-6d18-4c87-8c88-ccc3cad9cf4e · outbound

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

Agent Data Injection Attacks are Realistic Threats to AI Agents The dual llm pattern for building ai assistants that can resist prompt injection,

Reference 43

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e8ba3a0-d568-4feb-90df-954b596d3b68 · outbound

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

Agent Data Injection Attacks are Realistic Threats to AI Agents System-Level Defense against Indirect Prompt Injection Attacks: An Information Flow Control Perspective

Reference 44

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61fdd182-957a-42bf-a2e4-f3bd96768d0a · outbound

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

Agent Data Injection Attacks are Realistic Threats to AI Agents Securing AI Agents with Information-Flow Control

Reference 45

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56c5da6e-2985-40fb-8e97-bf2b4794304f · outbound

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

Agent Data Injection Attacks are Realistic Threats to AI Agents Permissive information-flow analysis for large language models,

Reference 46

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35e2a5b8-66c6-43c9-92ad-54bb216f8e7f · outbound

This paper cites How good are llms at processing tool outputs?.

Agent Data Injection Attacks are Realistic Threats to AI Agents How good are llms at processing tool outputs?

Reference 47

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed286d7a-9d26-4d38-b8a8-6d92d56097fb · outbound

This paper cites Llama prompt guard 2,.

Agent Data Injection Attacks are Realistic Threats to AI Agents Llama prompt guard 2,

Reference 48

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3b265e4-301c-4cfb-9d66-2d77b8258018 · outbound

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

Agent Data Injection Attacks are Realistic Threats to AI Agents React: Synergizing reasoning and acting in language models,

Reference 49

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a486fd7e-83da-4857-ac0c-66e3dfecfcc9 · outbound

This paper cites Great, now write an article about that: The crescendo {Multi-Turn}{LLM} jailbreak attack,.

Agent Data Injection Attacks are Realistic Threats to AI Agents Great, now write an article about that: The crescendo {Multi-Turn}{LLM} jailbreak attack,

Reference 50

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de4602ce-ebe3-40e8-91ec-10029032a4dd · outbound

This paper cites Universal adversarial triggers for attacking and analyzing NLP,.

Agent Data Injection Attacks are Realistic Threats to AI Agents Universal adversarial triggers for attacking and analyzing NLP,

Reference 51

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74448141-3b7a-41fc-ad64-a5e8e28087c0 · outbound

This paper cites Autodan: Generating stealthy jailbreak prompts on aligned large language models,.

Agent Data Injection Attacks are Realistic Threats to AI Agents Autodan: Generating stealthy jailbreak prompts on aligned large language models,

Reference 52

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06a654c9-40ef-48c7-8130-60f5110a5ffc · outbound

This paper cites Open sesame! universal black- box jailbreaking of large language models,.

Agent Data Injection Attacks are Realistic Threats to AI Agents Open sesame! universal black- box jailbreaking of large language models,

Reference 53

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4f301ce-b07e-4ab4-8cb8-6de2ca6b356d · outbound

This paper cites Jailbreak Attacks and Defenses Against Large Language Models: A Survey.

Agent Data Injection Attacks are Realistic Threats to AI Agents Jailbreak Attacks and Defenses Against Large Language Models: A Survey

Reference 54

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41b0f911-0f95-4b49-9d8c-f76431c2a69b · outbound

This paper cites Pleak: Prompt leaking attacks against large language model applications,.

Agent Data Injection Attacks are Realistic Threats to AI Agents Pleak: Prompt leaking attacks against large language model applications,

Reference 55

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0833b53e-7bac-4fb6-bbf1-bf3d0321e259 · outbound

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

Agent Data Injection Attacks are Realistic Threats to AI Agents Ignore Previous Prompt: Attack Techniques For Language Models

Reference 56

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8475828-cbb4-4a10-93df-e90e0ecbd824 · outbound

This paper cites Effective Prompt Extraction from Language Models.

Agent Data Injection Attacks are Realistic Threats to AI Agents Effective Prompt Extraction from Language Models

Reference 57

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51add82a-8060-4348-bbd4-2cf44c449ae3 · outbound

This paper cites Les dissonances: Cross-tool harvesting and polluting in multi-tool empowered llm agents,.

Agent Data Injection Attacks are Realistic Threats to AI Agents Les dissonances: Cross-tool harvesting and polluting in multi-tool empowered llm agents,

Reference 58

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc151831-632a-4836-9ca5-43723a7c1b6e · outbound

This paper cites Task injection – exploiting agency of autonomous ai agents,.

Agent Data Injection Attacks are Realistic Threats to AI Agents Task injection – exploiting agency of autonomous ai agents,

Reference 59

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4aa1d9cf-8616-4beb-9bf5-cd2622676114 · outbound

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

Agent Data Injection Attacks are Realistic Threats to AI Agents Optimization-based prompt injection attack to llm-as-a-judge,

Reference 60

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b0dca96-adff-4126-acdb-c100e9781103 · outbound

This paper cites Agentpoison: Red-teaming llm agents via poisoning memory or knowledge bases,.

Agent Data Injection Attacks are Realistic Threats to AI Agents Agentpoison: Red-teaming llm agents via poisoning memory or knowledge bases,

Reference 61

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df324fb1-a787-4af5-b498-94d104213b04 · outbound

This paper cites InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents.

Agent Data Injection Attacks are Realistic Threats to AI Agents InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents

Reference 62

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6709bc17-544d-4bfc-aab3-6a02e291add6 · outbound

This paper cites Benchmarking and defending against indirect prompt injection attacks on large language models,.

Agent Data Injection Attacks are Realistic Threats to AI Agents Benchmarking and defending against indirect prompt injection attacks on large language models,

Reference 63

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b14e7e5c-79ac-4608-8271-2138dfdce6fd · outbound

This paper cites WASP: Benchmarking web agent security against prompt injection attacks,.

Agent Data Injection Attacks are Realistic Threats to AI Agents WASP: Benchmarking web agent security against prompt injection attacks,

Reference 64

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b258b0a1-5a87-4228-ab68-c25d4736f567 · outbound

This paper cites Measuring Real-World Prompt Injection Attacks in LLM-based Resume Screening.

Agent Data Injection Attacks are Realistic Threats to AI Agents Measuring Real-World Prompt Injection Attacks in LLM-based Resume Screening

Reference 65

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 19955a6f-658c-4b33-a1af-67c02f4b52e5 · inbound

Refusal is Not Safety! Benchmarking Latent Safety Risks of LLM-Driven Content Humorization cites this paper.

Refusal is Not Safety! Benchmarking Latent Safety Risks of LLM-Driven Content Humorization Agent Data Injection Attacks are Realistic Threats to AI Agents

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-01T21:47:02.723794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.