Paper Citation Record · LEDGER

Prompt Injection 2.0: Hybrid AI Threats

As of 7 August 2026, this Paper Citation Record lists 29 of 29 outbound references and 3 inbound Pith citation observations for arXiv:2507.13169.

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

pith.paper-citation-record.v1
2507.13169 v1

Coverage vector

measured 29 of 29 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T16:34:05.446734Z

measured 32 of 32 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-22T12:46:44.819224Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-22T12:51:33.393440Z

Reference resolution

29 of 29 outbound references displayed

verified exact2
verified fuzzy1
unresolved25
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation e22e7f76-32cd-4cb3-869f-3183830e0afa · outbound

This paper cites Evaluating the Susceptibility of Pre-Trained Language Models via Handcrafted Adversarial Examples.

Prompt Injection 2.0: Hybrid AI Threats Evaluating the Susceptibility of Pre-Trained Language Models via Handcrafted Adversarial Examples

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T16:34:03.088522Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28fbf030-816c-41ff-903c-2df09f0a7f9c · outbound

This paper cites C., & Heichman, R.

Prompt Injection 2.0: Hybrid AI Threats C., & Heichman, R

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:34:08.065627Z

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 4ba24e3f-f487-4b02-a626-63b6ad009055 · outbound

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

Prompt Injection 2.0: Hybrid AI Threats Prompt Injection attack against LLM-integrated Applications

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T16:34:03.313953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 513e5f8c-0e6b-4d1c-aa3d-8110b7bcb807 · outbound

This paper cites Automatic and Universal Prompt Injection Attacks against Large Language Models.

Prompt Injection 2.0: Hybrid AI Threats Automatic and Universal Prompt Injection Attacks against Large Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T16:34:03.407180Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c8e481a-6979-4c1e-91d7-eb514330e081 · outbound

This paper cites From Prompt Injections to SQL Injection Attacks: How Protected is Your LLM-Integrated Web Application?.

Prompt Injection 2.0: Hybrid AI Threats From Prompt Injections to SQL Injection Attacks: How Protected is Your LLM-Integrated Web Application?

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T16:34:03.503194Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81b7056d-e92d-4262-a83a-cfadff70051b · outbound

This paper cites AI Ethics by Design: Implementing Customizable Guardrails for Responsible AI Development.

Prompt Injection 2.0: Hybrid AI Threats AI Ethics by Design: Implementing Customizable Guardrails for Responsible AI Development

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-08-06T16:34:06.402350Z

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 74108fff-12a9-4135-8e67-a6a18bca8085 · outbound

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

Prompt Injection 2.0: Hybrid AI Threats Design Patterns for Securing LLM Agents against Prompt Injections

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T16:34:03.695223Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ffcd4e8-6f3c-4856-9cce-4421416681fa · outbound

This paper cites an unresolved cited work.

Prompt Injection 2.0: Hybrid AI Threats Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-08-06T16:34:07.818080Z

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 67a374ee-c085-4de3-abb1-fb82d9c1fefe · outbound

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

Prompt Injection 2.0: Hybrid AI Threats Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T16:34:03.842222Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f4cdc41-655f-434b-9be2-a74bc3172ba9 · outbound

This paper cites Defeating Prompt Injections by Design.

Prompt Injection 2.0: Hybrid AI Threats Defeating Prompt Injections by Design

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T16:34:03.919189Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c073cff-1405-48a5-91aa-b7a78fc582b7 · outbound

This paper cites an unresolved cited work.

Prompt Injection 2.0: Hybrid AI Threats Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-08-06T16:34:07.505229Z

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 43d9d6d4-67cb-4608-89d9-d5c6532faf25 · outbound

This paper cites an unresolved cited work.

Prompt Injection 2.0: Hybrid AI Threats Unresolved cited work

Reference 12

Resolution: unresolved; raw_fallback, observed 2026-08-06T16:34:07.307622Z

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 0c024737-d7c3-4a78-9b2f-f2c999750230 · outbound

This paper cites an unresolved cited work.

Prompt Injection 2.0: Hybrid AI Threats Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-08-06T16:34:07.022398Z

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 2783b487-2406-40aa-aff0-c2ebdf3fd4ae · outbound

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

Prompt Injection 2.0: Hybrid AI Threats Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T16:34:04.277916Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 932b69ab-e882-49e0-a697-a9bbcf822bb9 · outbound

This paper cites an unresolved cited work.

Prompt Injection 2.0: Hybrid AI Threats Unresolved cited work

Reference 15

Resolution: unresolved; raw_fallback, observed 2026-08-06T16:34:06.877652Z

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 e379a488-61be-486e-b10a-30e052f70bbd · outbound

This paper cites XOXO: Stealthy Cross-Origin Context Poisoning Attacks against AI Coding Assistants.

Prompt Injection 2.0: Hybrid AI Threats XOXO: Stealthy Cross-Origin Context Poisoning Attacks against AI Coding Assistants

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-08-06T16:34:06.094966Z

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 97ca63c5-25a5-4980-94cb-1c29107c98e0 · outbound

This paper cites The Hidden Dangers of Browsing AI Agents.

Prompt Injection 2.0: Hybrid AI Threats The Hidden Dangers of Browsing AI Agents

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T16:34:04.510763Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48ce344e-7e62-45bd-8d86-18374023e328 · outbound

This paper cites Learning to Poison Large Language Models for Downstream Manipulation.

Prompt Injection 2.0: Hybrid AI Threats Learning to Poison Large Language Models for Downstream Manipulation

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T16:34:04.598552Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb31b710-e5d8-497a-9bb8-b335be88601d · outbound

This paper cites Human-Imperceptible Retrieval Poisoning Attacks in LLM-Powered Applications.

Prompt Injection 2.0: Hybrid AI Threats Human-Imperceptible Retrieval Poisoning Attacks in LLM-Powered Applications

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T16:34:04.667309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a60a853-a16d-4b30-beb5-e095804b0e30 · outbound

This paper cites Invisible Prompts, Visible Threats: Malicious Font Injection in External Resources for Large Language Models.

Prompt Injection 2.0: Hybrid AI Threats Invisible Prompts, Visible Threats: Malicious Font Injection in External Resources for Large Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T16:34:04.754226Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbe5eca5-fc2b-4390-98d2-c32b7d9b82ac · outbound

This paper cites Backdoored Retrievers for Prompt Injection Attacks on Retrieval Augmented Generation of Large Language Models.

Prompt Injection 2.0: Hybrid AI Threats Backdoored Retrievers for Prompt Injection Attacks on Retrieval Augmented Generation of Large Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T16:34:04.853306Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a247095-3659-4852-b88a-22fed94a42b8 · outbound

This paper cites Manipulating Multimodal Agents via Cross-Modal Prompt Injection.

Prompt Injection 2.0: Hybrid AI Threats Manipulating Multimodal Agents via Cross-Modal Prompt Injection

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T16:34:04.952025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6514fbca-975f-4253-a587-05efbc389ff9 · outbound

This paper cites an unresolved cited work.

Prompt Injection 2.0: Hybrid AI Threats Unresolved cited work

Reference 23

Resolution: unresolved; raw_fallback, observed 2026-08-06T16:34:06.771915Z

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 80107157-42c9-4510-a17b-5ec0990ce669 · outbound

This paper cites Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs.

Prompt Injection 2.0: Hybrid AI Threats Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T16:34:05.101373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 711b04e6-a84a-4b06-8648-54f847ee47d8 · outbound

This paper cites Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs through a Global Scale Prompt Hacking Competition.

Prompt Injection 2.0: Hybrid AI Threats Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs through a Global Scale Prompt Hacking Competition

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T16:34:05.169846Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 901f6257-6605-4160-b812-d5c36cc18a4a · outbound

This paper cites an unresolved cited work.

Prompt Injection 2.0: Hybrid AI Threats Unresolved cited work

Reference 26

Resolution: malformed identifier; raw_fallback, observed 2026-08-06T16:34:06.657603Z

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 53d2c546-ea9f-4636-bf87-72f6c0317db7 · outbound

This paper cites LLM Agents can Autonomously Hack Websites.

Prompt Injection 2.0: Hybrid AI Threats LLM Agents can Autonomously Hack Websites

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T16:34:05.325342Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a6efbb7-8971-44ae-aabf-67ad24ecb2ae · outbound

This paper cites Here Comes The AI Worm: Unleashing Zero-click Worms that Target GenAI-Powered Applications.

Prompt Injection 2.0: Hybrid AI Threats Here Comes The AI Worm: Unleashing Zero-click Worms that Target GenAI-Powered Applications

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T16:34:05.379319Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a6b4405-be54-4aaf-bad0-de88deabf587 · outbound

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

Prompt Injection 2.0: Hybrid AI Threats Defending Against Indirect Prompt Injection Attacks With Spotlighting

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T16:34:05.446734Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation e5e416d9-e605-440c-b626-69eb3f50bd19 · inbound

Neuro-Symbolic AI for Cybersecurity: State of the Art, Challenges, and Opportunities cites this paper.

Neuro-Symbolic AI for Cybersecurity: State of the Art, Challenges, and Opportunities Prompt Injection 2.0: Hybrid AI Threats

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-18T18:06:43.025006Z

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 406e2f80-5836-4e26-8605-0a1161a23245 · inbound

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

Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges Prompt Injection 2.0: Hybrid AI Threats

Reference 61

Resolution: verified exact; arxiv_id, observed 2026-05-18T03:42:22.431852Z

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 621df737-31d9-4a80-9d4e-e92f691c623e · inbound

Semantic Attacks on Tool-Augmented LLMs: Securing the Model Context Protocol Against Descriptor-Level Manipulation cites this paper.

Semantic Attacks on Tool-Augmented LLMs: Securing the Model Context Protocol Against Descriptor-Level Manipulation Prompt Injection 2.0: Hybrid AI Threats

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-05-22T12:51:33.396810Z

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.