Paper Citation Record · LEDGER

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

As of 18 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 27 inbound Pith citation observations for arXiv:2502.05174.

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

pith.paper-citation-record.v1
2502.05174 v4

Coverage vector

measured 39 of 39 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-08T20:06:58.396831Z

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 27 of 27 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-14T04:23:15.028834Z

measured 1 of 1 external citation measurements

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

Source: pith, observed 2026-08-05T02:28:24.338817Z

Reference resolution

39 of 39 outbound references displayed

verified exact0
verified fuzzy17
unresolved22
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

0
pith, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation bf1d06bc-9a3e-448a-8ba7-829bd0768f4e · outbound

This paper cites write newline.

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-08T20:06:58.210635Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dea9f8ed-8631-4d93-a512-34e00a5d8c8f · outbound

This paper cites https://learnprompting.org/docs/prompt_hacking/defensive_measures/sandwich_defense, 2023.

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents https://learnprompting.org/docs/prompt_hacking/defensive_measures/sandwich_defense, 2023

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:06:58.975034Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7b77f22d-bffb-416f-a020-46cc078078a2 · outbound

This paper cites Claude 3.5 models and computer use, 2024.

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents Claude 3.5 models and computer use, 2024

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:06:58.961017Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b80735f8-ab6a-4cc9-9bf5-ddab069b1e30 · outbound

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

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents StruQ: Defending Against Prompt Injection with Structured Queries

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-08T20:06:58.227628Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9dae070a-56be-4e5f-b63a-539284747a04 · outbound

This paper cites SecAlign: Defending Against Prompt Injection with Preference Optimization.

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents SecAlign: Defending Against Prompt Injection with Preference Optimization

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-08T20:06:58.233116Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84b70a05-e67c-4f99-960d-baf286abf793 · outbound

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

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents Agentdojo: A dynamic environment to evaluate prompt injection attacks and defenses for llm agents

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:06:58.946981Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 292d00cc-2e23-4846-914f-3dc3ae942497 · outbound

This paper cites Deepseek function calling guide.

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents Deepseek function calling guide

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:06:58.932465Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 223ee63e-2043-45f2-bff2-5f55c802e61d · outbound

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

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents Defending Against Indirect Prompt Injection Attacks With Spotlighting

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-08T20:06:58.248872Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1dc6c89-9d97-48be-a6eb-b3b54354f6ec · outbound

This paper cites Attention Tracker: Detecting Prompt Injection Attacks in LLMs.

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents Attention Tracker: Detecting Prompt Injection Attacks in LLMs

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-08T20:06:58.253925Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6975a179-af4f-48af-95dc-e328b3791da9 · outbound

This paper cites Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations.

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-08T20:06:58.258918Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81c623e0-dee3-419b-9334-f00aa2f7ef84 · outbound

This paper cites EIA: Environmental Injection Attack on Generalist Web Agents for Privacy Leakage.

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents EIA: Environmental Injection Attack on Generalist Web Agents for Privacy Leakage

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-08T20:06:58.263834Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f927fbde-b04d-4b53-8ffb-d1a5ce0c29d2 · outbound

This paper cites an unresolved cited work.

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents Unresolved cited work

Reference 12

Resolution: unresolved; raw_fallback, observed 2026-08-08T20:06:58.917814Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 2958124b-7daa-4ad6-9b3d-69e447113e6f · outbound

This paper cites Llama3.3 model cards, 2024.

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents Llama3.3 model cards, 2024

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:06:58.902871Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 2300653e-959b-4b9f-81f3-71f10a7ff7dc · outbound

This paper cites Ultimate ChatGPT prompt engineering guide for general users and developers.

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents Ultimate ChatGPT prompt engineering guide for general users and developers

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:06:58.888824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 3c8a0ba8-6613-4941-80b3-81b203a0e047 · outbound

This paper cites Testing Language Model Agents Safely in the Wild.

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents Testing Language Model Agents Safely in the Wild

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-08T20:06:58.282814Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8786f57-27dc-434f-9fea-c06eba48afa7 · outbound

This paper cites Openai text embeddings, 2024.

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents Openai text embeddings, 2024

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:06:58.874469Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 4d3cfb36-3fbd-498f-a0ef-efef24db98f6 · outbound

This paper cites Openai function calling guide, 2024.

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents Openai function calling guide, 2024

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:06:58.859955Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ed056a33-5c43-4096-9f46-5aad6e97aea0 · outbound

This paper cites GoEX: Perspectives and Designs Towards a Runtime for Autonomous LLM Applications.

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents GoEX: Perspectives and Designs Towards a Runtime for Autonomous LLM Applications

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-08T20:06:58.296667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15640117-b63f-482d-acfd-5ba149c2421a · outbound

This paper cites and Ribeiro, I.

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents and Ribeiro, I

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:06:58.844863Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation fa310591-321c-4cb8-9946-08b5fb4d3ea7 · outbound

This paper cites Fine-tuned deberta-v3-base for prompt injection detection, 2024.

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents Fine-tuned deberta-v3-base for prompt injection detection, 2024

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:06:58.829647Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b9f42e10-c581-4f3f-9cea-e68f9267f892 · outbound

This paper cites J., and Hashimoto, T.

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents J., and Hashimoto, T

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:06:58.813875Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation bab47efd-26d4-4e4e-87e7-df91a32a3d55 · outbound

This paper cites Ignore this title and H ack AP rompt: Exposing systemic vulnerabilities of LLM s through a global prompt hacking competition.

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents Ignore this title and H ack AP rompt: Exposing systemic vulnerabilities of LLM s through a global prompt hacking competition

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-08T20:06:58.316068Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f52a6040-3dc9-475a-a901-78344b38a012 · outbound

This paper cites A., Svegliato, J., Bailey, L., Wang, T., Ong, I., Elmaaroufi, K., Abbeel, P., Darrell, T., Ritter, A., and Russell, S.

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents A., Svegliato, J., Bailey, L., Wang, T., Ong, I., Elmaaroufi, K., Abbeel, P., Darrell, T., Ritter, A., and Russell, S

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:06:58.798731Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ee407b4a-e4f6-47c2-b901-5d6f7b07b83b · outbound

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

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-08T20:06:58.325586Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b492243-a40a-46b2-99eb-196c045e6598 · outbound

This paper cites Prompt injection attacks against GPT-3.

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents Prompt injection attacks against GPT-3

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:06:58.782338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation f2a6f917-3765-4e79-9c51-501658165f08 · outbound

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

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents Delimiters won’t save you from prompt injection

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:06:58.767633Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6a90feb9-8f8c-46df-9d07-11fed6300970 · outbound

This paper cites Dissecting Adversarial Robustness of Multimodal LM Agents.

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents Dissecting Adversarial Robustness of Multimodal LM Agents

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-08T20:06:58.339855Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90c09a10-0c7b-4026-acca-d88284c82bed · outbound

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

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents System-Level Defense against Indirect Prompt Injection Attacks: An Information Flow Control Perspective

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-08T20:06:58.344908Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d187030-68c4-41d5-8272-38aaf24193f0 · outbound

This paper cites A New Era in LLM Security: Exploring Security Concerns in Real-World LLM-based Systems.

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents A New Era in LLM Security: Exploring Security Concerns in Real-World LLM-based Systems

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-08T20:06:58.349652Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f395f473-974b-4c1b-90aa-e96b3dcf682c · outbound

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

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents IsolateGPT: An Execution Isolation Architecture for LLM-Based Systems

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:06:58.752762Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 51c834a0-bcc7-4ef8-ae66-97d23a97fdcf · outbound

This paper cites AdvAgent: Controllable Blackbox Red-teaming on Web Agents.

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents AdvAgent: Controllable Blackbox Red-teaming on Web Agents

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-08T20:06:58.358737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a54c5ddd-84e9-4792-90b9-959a80102c65 · outbound

This paper cites Assessing Prompt Injection Risks in 200+ Custom GPTs.

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents Assessing Prompt Injection Risks in 200+ Custom GPTs

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-08T20:06:58.363694Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9728db56-fcdf-4bc8-9110-f538457876f7 · outbound

This paper cites R-judge: Benchmarking safety risk awareness for LLM agents.

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents R-judge: Benchmarking safety risk awareness for LLM agents

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:06:58.737887Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b9ef8ef5-a886-4dba-b054-fc56eaea1a55 · outbound

This paper cites I njec A gent: Benchmarking indirect prompt injections in tool-integrated large language model agents.

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents I njec A gent: Benchmarking indirect prompt injections in tool-integrated large language model agents

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-08T20:06:58.372999Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68c84e93-8235-4f7b-91ac-d9b1d83476b2 · outbound

This paper cites Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents.

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-08T20:06:58.377603Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4dbf589f-f2cd-4380-a814-c3ac8c22a68a · outbound

This paper cites Attacking vision-language computer agents via pop-ups, 2024 b.

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents Attacking vision-language computer agents via pop-ups, 2024 b

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:06:58.722556Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6e8a3080-e8a4-4803-9599-75eaf82c2e79 · outbound

This paper cites Poisoning retrieval corpora by injecting adversarial passages.

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents Poisoning retrieval corpora by injecting adversarial passages

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-08T20:06:58.387249Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ec90ab3-1ff6-4bcb-9c8a-40b346d24fd5 · outbound

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

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-08T20:06:58.391995Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27efaa9a-50aa-4e30-87aa-399eeb3fc73b · outbound

This paper cites PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models.

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-08T20:06:58.396831Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation bc0da62c-e2b2-4b9e-9729-d62b6bba9bf5 · inbound

Robustness via Referencing: Defending against Prompt Injection Attacks by Referencing the Executed Instruction cites this paper.

Robustness via Referencing: Defending against Prompt Injection Attacks by Referencing the Executed Instruction MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents

Reference 49

Resolution: verified exact; arxiv_id, observed 2026-05-22T19:11:58.071951Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation cf50d8e3-a96a-4a81-9b6d-0591876bad5e · inbound

Red-Teaming Coding Agents from a Tool-Invocation Perspective: An Empirical Security Assessment cites this paper.

Red-Teaming Coding Agents from a Tool-Invocation Perspective: An Empirical Security Assessment MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-05T05:09:40.020584Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f04d6e3a-abbb-4b23-900d-a43dd7764acf · inbound

Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges cites this paper.

Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents

Reference 72

Resolution: verified exact; arxiv_id, observed 2026-05-18T03:42:22.076283Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 83db55d0-db33-4d19-ae2a-643819ab73e1 · inbound

Whispers of Wealth: Red-Teaming Google's Agent Payments Protocol via Prompt Injection cites this paper.

Whispers of Wealth: Red-Teaming Google's Agent Payments Protocol via Prompt Injection MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-21T15:20:17.375618Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation eaa09e39-4804-40ab-97b3-d721ad91f20f · inbound

Beyond Pattern Matching: Seven Cross-Domain Techniques for Prompt Injection Detection cites this paper.

Beyond Pattern Matching: Seven Cross-Domain Techniques for Prompt Injection Detection MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-10T11:55:21.358611Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation dc536703-e33e-4e4c-810f-60d43b326d45 · inbound

Beyond Pattern Matching: Seven Cross-Domain Techniques for Prompt Injection Detection cites this paper.

Beyond Pattern Matching: Seven Cross-Domain Techniques for Prompt Injection Detection MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-21T00:53:53.086682Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 27bc2e11-4352-471d-ba9a-ac370452f911 · inbound

Beyond Pattern Matching: Seven Cross-Domain Techniques for Prompt Injection Detection cites this paper.

Beyond Pattern Matching: Seven Cross-Domain Techniques for Prompt Injection Detection MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-02T15:56:49.153150Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af9bf477-2843-42a9-acb7-81f110a10627 · inbound

AgentVisor: Defending LLM Agents Against Prompt Injection via Semantic Virtualization cites this paper.

AgentVisor: Defending LLM Agents Against Prompt Injection via Semantic Virtualization MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents

Reference 19

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T22:16:30.500382Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 27d2da28-7187-47eb-9ce5-535bf8f5b342 · inbound

PIIGuard: Mitigating PII Harvesting under Adversarial Sanitization cites this paper.

PIIGuard: Mitigating PII Harvesting under Adversarial Sanitization MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-08T17:53:53.269765Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation e4adebc1-6504-4c7c-8f20-a8d6b2fd0806 · inbound

ARGUS: Defending LLM Agents Against Context-Aware Prompt Injection cites this paper.

ARGUS: Defending LLM Agents Against Context-Aware Prompt Injection MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents

Reference 21

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T23:56:13.752504Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b5f50e10-3b71-4af1-8562-22cb40fb556b · inbound

AgentShield: Deception-based Compromise Detection for Tool-using LLM Agents cites this paper.

AgentShield: Deception-based Compromise Detection for Tool-using LLM Agents MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-13T01:32:02.602437Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation e8a283c1-48e1-42d5-9cd8-fe9247005d92 · inbound

The Granularity Mismatch in Agent Security: Argument-Level Provenance Solves Enforcement and Isolates the LLM Reasoning Bottleneck cites this paper.

The Granularity Mismatch in Agent Security: Argument-Level Provenance Solves Enforcement and Isolates the LLM Reasoning Bottleneck MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-05-13T01:32:02.864173Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 692f3850-3a5e-4ad4-8cad-e516b7b8185c · inbound

LivePI: More Realistic Benchmarking of Agents Against Indirect Prompt Injection cites this paper.

LivePI: More Realistic Benchmarking of Agents Against Indirect Prompt Injection MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-20T10:03:14.260886Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 91bae419-35f8-4a06-987b-eadb178dd4bf · inbound

LivePI: More Realistic Benchmarking of Agents Against Indirect Prompt Injection cites this paper.

LivePI: More Realistic Benchmarking of Agents Against Indirect Prompt Injection MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-06-30T18:55:00.614674Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation dc44d31b-78bd-47b2-8f94-db0762f749a9 · inbound

Reframing LLM Agent Security as an Agent-Human Interaction Problem cites this paper.

Reframing LLM Agent Security as an Agent-Human Interaction Problem MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents

Reference 68

Resolution: verified exact; arxiv_id, observed 2026-06-30T13:54:43.862943Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 727f71f4-65f5-463d-aabb-c7f8ff8c006b · inbound

AIRGuard: Guarding Agent Actions with Runtime Authority Control cites this paper.

AIRGuard: Guarding Agent Actions with Runtime Authority Control MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-06-29T12:53:27.162560Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7b8f0d67-b24c-4feb-bfce-0496f8f3e59f · inbound

Depth-Dependent Indirect Prompt Injection in Tool-Calling ReAct Agents: Injection Depth, Payload Framing, and Turn-Budget Sensitivity cites this paper.

Depth-Dependent Indirect Prompt Injection in Tool-Calling ReAct Agents: Injection Depth, Payload Framing, and Turn-Budget Sensitivity MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-06-28T22:32:43.991088Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 87627205-3b01-4073-870b-ecf8c197cf77 · inbound

Same Payload, Different Channel: Measuring Trust Asymmetry in Tool-Using Language Models cites this paper.

Same Payload, Different Channel: Measuring Trust Asymmetry in Tool-Using Language Models MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents

Reference 17

Resolution: metadata mismatch; arxiv_id, observed 2026-06-28T19:22:34.416763Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation e1954abd-ca21-444a-a120-b1ed758cffee · inbound

Think Twice Before You Act: Protecting LLM Agents Against Tool Description Poisoning via Isolated Planning cites this paper.

Think Twice Before You Act: Protecting LLM Agents Against Tool Description Poisoning via Isolated Planning MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents

Reference 22

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T04:59:36.379930Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d79a76aa-5e44-4487-b491-db217ecb54fc · inbound

When AUC 0.998 Is Not Enough: A Candidate Evaluation Protocol for Hidden-State Probes of Indirect Prompt Injection in Multimodal Computer-Use Agents cites this paper.

When AUC 0.998 Is Not Enough: A Candidate Evaluation Protocol for Hidden-State Probes of Indirect Prompt Injection in Multimodal Computer-Use Agents MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents

Reference 53

Resolution: verified exact; arxiv_id, observed 2026-07-04T10:09:45.221940Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

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

DualView: Preventing Indirect Prompt Injection in Personal AI Agents cites this paper.

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 8788fdd6-120c-41e7-ba17-e306332bd7e0 · inbound

The Balkanization of Execution-Security Research for AI Coding Agents: Isolation, Access Control, and Time-of-Check-to-Time-of-Use Vulnerabilities cites this paper.

The Balkanization of Execution-Security Research for AI Coding Agents: Isolation, Access Control, and Time-of-Check-to-Time-of-Use Vulnerabilities MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents

Reference 51

Resolution: verified exact; local_arxiv, observed 2026-07-11T02:47:50.246193Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7409786b-0f30-4634-bcd7-e1b343f720f1 · inbound

Agent Security Needs Redefinition through a Holistic Framework cites this paper.

Agent Security Needs Redefinition through a Holistic Framework MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents

Reference 206

Resolution: unresolved; no resolver link, observed 2026-08-01T06:04:46.304739Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2ebbed9-42ad-4d66-a74d-b17e01676a42 · inbound

Beyond Single-Use Tokens: Durable Authorization State for Replay-Resistant LLM Agent Actions cites this paper.

Beyond Single-Use Tokens: Durable Authorization State for Replay-Resistant LLM Agent Actions MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T22:27:22.453591Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7de49ffb-9ea8-48b1-bdce-4bda27c3e421 · inbound

AgentAntibody: An Adaptive Immune System for Defending LLM Agents against Prompt Injection cites this paper.

AgentAntibody: An Adaptive Immune System for Defending LLM Agents against Prompt Injection MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:38.030612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4992c41-56f8-4f5f-aa4a-0a8bde72ae61 · inbound

Robust Context-Aware Detection of Malicious Instructions in Text cites this paper.

Robust Context-Aware Detection of Malicious Instructions in Text MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-08T13:19:01.988614Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54992195-e40d-41b8-bca5-1cc9f50365a6 · inbound

Not an A11y: How Android Accessibility Exposes Mobile AI Agents to Indirect Prompt Injection cites this paper.

Not an A11y: How Android Accessibility Exposes Mobile AI Agents to Indirect Prompt Injection MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-14T04:23:15.028834Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.