Paper Citation Record · LEDGER

The Obvious Invisible Threat: LLM-Powered GUI Agents' Vulnerability to Fine-Print Injections

As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 18 inbound Pith citation observations for arXiv:2504.11281.

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

pith.paper-citation-record.v1
2504.11281 v1

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 18 of 18 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 18 of 18 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:41:25.119934Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-02T17:37:14.704219Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation baf02ff0-1b57-416d-a408-90a52e025bba · inbound

EVA: Evolving Semantic Adversaries for Red-Teaming GUI Agents Against Environmental Injection Attacks cites this paper.

EVA: Evolving Semantic Adversaries for Red-Teaming GUI Agents Against Environmental Injection Attacks The Obvious Invisible Threat: LLM-Powered GUI Agents' Vulnerability to Fine-Print Injections

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T15:41:25.119934Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 150a8806-5a0c-47bd-bad3-3e2fe54f5d5d · inbound

Get Experience from Practice: LLM Agents with Record & Replay cites this paper.

Get Experience from Practice: LLM Agents with Record & Replay The Obvious Invisible Threat: LLM-Powered GUI Agents' Vulnerability to Fine-Print Injections

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T14:44:22.237391Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f5c4307-9121-4ec8-83ab-86af83737893 · inbound

Superplatforms Have to Attack AI Agents cites this paper.

Superplatforms Have to Attack AI Agents The Obvious Invisible Threat: LLM-Powered GUI Agents' Vulnerability to Fine-Print Injections

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:36.620074Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4f3d604-3347-46d1-9a55-af913c0b0a43 · inbound

MLA-Trust: Benchmarking Trustworthiness of Multimodal LLM Agents in GUI Environments cites this paper.

MLA-Trust: Benchmarking Trustworthiness of Multimodal LLM Agents in GUI Environments The Obvious Invisible Threat: LLM-Powered GUI Agents' Vulnerability to Fine-Print Injections

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-07T11:42:34.196721Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30c1c094-28c6-4366-84f6-883adf8665bb · inbound

A Red Teaming Roadmap Towards System-Level Safety cites this paper.

A Red Teaming Roadmap Towards System-Level Safety The Obvious Invisible Threat: LLM-Powered GUI Agents' Vulnerability to Fine-Print Injections

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T12:11:18.999964Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22d115e0-8aca-4c8c-bb73-4c8cc98bfe99 · inbound

A Survey on Autonomy-Induced Security Risks in Large Model-Based Agents cites this paper.

A Survey on Autonomy-Induced Security Risks in Large Model-Based Agents The Obvious Invisible Threat: LLM-Powered GUI Agents' Vulnerability to Fine-Print Injections

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T21:34:41.144903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99296258-533c-4967-8ff6-35c670ae96a8 · inbound

LaSM: Layer-wise Scaling Mechanism for Defending Pop-up Attack on GUI Agents cites this paper.

LaSM: Layer-wise Scaling Mechanism for Defending Pop-up Attack on GUI Agents The Obvious Invisible Threat: LLM-Powered GUI Agents' Vulnerability to Fine-Print Injections

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-19T04:12:02.144146Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1095f92a-4d4e-47c4-a14f-766e8757ff8c · inbound

WebGuard: Building a Generalizable Guardrail for Web Agents cites this paper.

WebGuard: Building a Generalizable Guardrail for Web Agents The Obvious Invisible Threat: LLM-Powered GUI Agents' Vulnerability to Fine-Print Injections

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T16:12:47.459876Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3822e4e0-dbff-4d16-9b92-1cf9f2f10c2f · inbound

Towards Aligning Personalized Conversational Recommendation Agents with Users' Privacy Preferences cites this paper.

Towards Aligning Personalized Conversational Recommendation Agents with Users' Privacy Preferences The Obvious Invisible Threat: LLM-Powered GUI Agents' Vulnerability to Fine-Print Injections

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-05T22:01:05.327178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9d787bb-0a79-4f97-b984-840f0d353a57 · inbound

Dark Patterns Meet GUI Agents: LLM Agent Susceptibility to Manipulative Interfaces and the Role of Human Oversight cites this paper.

Dark Patterns Meet GUI Agents: LLM Agent Susceptibility to Manipulative Interfaces and the Role of Human Oversight The Obvious Invisible Threat: LLM-Powered GUI Agents' Vulnerability to Fine-Print Injections

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T17:40:08.160733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5146ffee-6d90-4e45-9314-8dedadf7d659 · inbound

Autonomy Reshapes How Personalization Affects Privacy Concerns and Trust in LLM Agents cites this paper.

Autonomy Reshapes How Personalization Affects Privacy Concerns and Trust in LLM Agents The Obvious Invisible Threat: LLM-Powered GUI Agents' Vulnerability to Fine-Print Injections

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-18T10:11:13.880302Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f2a96975-04c3-41cd-a0c8-b187b68935bc · inbound

CaMeLs Can Use Computers Too: System-level Security for Computer Use Agents cites this paper.

CaMeLs Can Use Computers Too: System-level Security for Computer Use Agents The Obvious Invisible Threat: LLM-Powered GUI Agents' Vulnerability to Fine-Print Injections

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-03T10:32:32.852827Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f39ac8c-c74c-4d40-abba-3c33d4fbbc1b · inbound

Mind the Gap: Action Rebinding Attacks against Android GUI Agents cites this paper.

Mind the Gap: Action Rebinding Attacks against Android GUI Agents The Obvious Invisible Threat: LLM-Powered GUI Agents' Vulnerability to Fine-Print Injections

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-03T09:54:55.575192Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eea0e0d4-23ec-42de-ad4f-66cd3c8f0548 · 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 The Obvious Invisible Threat: LLM-Powered GUI Agents' Vulnerability to Fine-Print Injections

Reference 57

Resolution: verified exact; arxiv_id, observed 2026-05-16T11:32:48.261369Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation db497fee-adff-4c88-a91f-7bcb345df51c · inbound

Comparing Human Oversight Strategies for Computer-Use Agents cites this paper.

Comparing Human Oversight Strategies for Computer-Use Agents The Obvious Invisible Threat: LLM-Powered GUI Agents' Vulnerability to Fine-Print Injections

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-10T22:30:50.458769Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d18b954f-e445-4913-8b7d-1d324e9fe442 · inbound

DPAgent-in-the-Middle: Agentic Defense and Repair Against AI-Groomed Deceptive Patterns cites this paper.

DPAgent-in-the-Middle: Agentic Defense and Repair Against AI-Groomed Deceptive Patterns The Obvious Invisible Threat: LLM-Powered GUI Agents' Vulnerability to Fine-Print Injections

Reference 49

Resolution: verified exact; arxiv_id, observed 2026-07-02T17:37:14.706066Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation a131bc1f-eef1-4277-a050-59151844c565 · inbound

Invisible Ink Threats: Adversarial Goals Behind Legitimate Tasks in Computer-Use Agents cites this paper.

Invisible Ink Threats: Adversarial Goals Behind Legitimate Tasks in Computer-Use Agents The Obvious Invisible Threat: LLM-Powered GUI Agents' Vulnerability to Fine-Print Injections

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-04T16:36:53.204683Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6e545e5-2312-4aec-81e7-14b2b7e4ff67 · inbound

Invisible Ink Threats: Adversarial Goals Behind Legitimate Tasks in Computer-Use Agents cites this paper.

Invisible Ink Threats: Adversarial Goals Behind Legitimate Tasks in Computer-Use Agents The Obvious Invisible Threat: LLM-Powered GUI Agents' Vulnerability to Fine-Print Injections

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T00:59:39.211103Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.