Paper Citation Record · LEDGER

A Systematization of Security Vulnerabilities in Computer Use Agents

As of 7 August 2026, this Paper Citation Record lists 21 of 21 outbound references and 4 inbound Pith citation observations for arXiv:2507.05445.

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

pith.paper-citation-record.v1
2507.05445 v1

Coverage vector

measured 21 of 21 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T19:29:54.026039Z

measured 25 of 25 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-03T09:54:57.493112Z

measured 1 of 1 external citation measurements

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

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

Reference resolution

21 of 21 outbound references displayed

verified exact0
verified fuzzy11
unresolved9
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

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

Outbound references

Observation 2c5ae4a9-0f4a-4d18-9edc-59d9b2993dc7 · outbound

This paper cites Osworld: Benchmarking multimodal agents for open-ended tasks in real computer environments,.

A Systematization of Security Vulnerabilities in Computer Use Agents Osworld: Benchmarking multimodal agents for open-ended tasks in real computer environments,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:29:57.504280Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 98314f42-e14d-4148-a681-3ac05e9d1eaa · outbound

This paper cites Operator system card,.

A Systematization of Security Vulnerabilities in Computer Use Agents Operator system card,

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:29:57.206439Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation e00b2d44-7333-498f-bb0b-8511f017eb28 · outbound

This paper cites Developing a computer use model,.

A Systematization of Security Vulnerabilities in Computer Use Agents Developing a computer use model,

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:29:56.964829Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 396a6059-6148-4ef6-b660-eeb21578bcc0 · outbound

This paper cites Project Astra: Multimodal AI Assistants,.

A Systematization of Security Vulnerabilities in Computer Use Agents Project Astra: Multimodal AI Assistants,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:29:56.655400Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 178ed3ab-35c5-4cf8-8bfb-9d1d531330c4 · outbound

This paper cites Tell me, what are you most afraid of? Exploring the Effects of Agent Representation on Information Disclosure in Human-Chatbot Interaction.

A Systematization of Security Vulnerabilities in Computer Use Agents Tell me, what are you most afraid of? Exploring the Effects of Agent Representation on Information Disclosure in Human-Chatbot Interaction

Reference 5

Resolution: metadata mismatch; local_arxiv, observed 2026-08-06T19:29:54.389245Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1573ad1d-0fd5-4f94-8be9-da1b4eb335b9 · outbound

This paper cites Hello gpt-4o,.

A Systematization of Security Vulnerabilities in Computer Use Agents Hello gpt-4o,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:29:56.390520Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 85b7d1bc-eae4-4750-85ac-b64822e7cbcf · outbound

This paper cites ReAct: Synergizing Reasoning and Acting in Language Models.

A Systematization of Security Vulnerabilities in Computer Use Agents ReAct: Synergizing Reasoning and Acting in Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T19:29:52.169152Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fdb3d9f0-2aa6-4218-8a1e-8f3ee26ff203 · outbound

This paper cites Reflexion: Language Agents with Verbal Reinforcement Learning.

A Systematization of Security Vulnerabilities in Computer Use Agents Reflexion: Language Agents with Verbal Reinforcement Learning

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T19:29:52.269959Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cba173f1-9883-4ec5-b723-bef3f93899bb · outbound

This paper cites Red Teaming Language Models with Language Models.

A Systematization of Security Vulnerabilities in Computer Use Agents Red Teaming Language Models with Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T19:29:52.397415Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79d601b8-8a3f-4fd5-b438-cd9aa93d5d4f · outbound

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

A Systematization of Security Vulnerabilities in Computer Use Agents Ignore Previous Prompt: Attack Techniques For Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T19:29:52.554579Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6db69d7-b6fc-489e-a989-964a2dc1024c · outbound

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

A Systematization of Security Vulnerabilities in Computer Use Agents Prompt Injection attack against LLM-integrated Applications

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T19:29:52.672797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5638b48c-59fa-44dc-b712-2d22af042eaf · outbound

This paper cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models.

A Systematization of Security Vulnerabilities in Computer Use Agents Chain-of-Thought Prompting Elicits Reasoning in Large Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T19:29:52.818079Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a89e7da2-0fcd-4f3b-9963-83564f8a3383 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

A Systematization of Security Vulnerabilities in Computer Use Agents DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T19:29:52.931899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e51e3a2-faff-41f9-8f52-95feb05b7748 · outbound

This paper cites WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models.

A Systematization of Security Vulnerabilities in Computer Use Agents WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T19:29:53.054555Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e3c3894-2598-4393-8ac4-428333da0efa · outbound

This paper cites LLMAuditor: A Framework for Auditing Large Language Models Using Human-in-the-Loop.

A Systematization of Security Vulnerabilities in Computer Use Agents LLMAuditor: A Framework for Auditing Large Language Models Using Human-in-the-Loop

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T19:29:53.202993Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f77d285a-97a6-4c6e-b9e7-743a42db37f3 · outbound

This paper cites Preventing ai hallucinations with human-in-the-loop test- ing,.

A Systematization of Security Vulnerabilities in Computer Use Agents Preventing ai hallucinations with human-in-the-loop test- ing,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:29:56.084386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 5855dcb5-14eb-414a-8cb3-09c250c74116 · outbound

This paper cites Reducing hallucinations in large language models with custom intervention using amazon bedrock agents,.

A Systematization of Security Vulnerabilities in Computer Use Agents Reducing hallucinations in large language models with custom intervention using amazon bedrock agents,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:29:55.816777Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c7df287c-8d36-434a-9a8a-ba965ec6cfb5 · outbound

This paper cites Prompt injection attacks in multimodal and tool-augmented language models,.

A Systematization of Security Vulnerabilities in Computer Use Agents Prompt injection attacks in multimodal and tool-augmented language models,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:29:55.488803Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a1502e58-5060-4b25-976a-98be8d422714 · outbound

This paper cites ”human in the loop.

A Systematization of Security Vulnerabilities in Computer Use Agents ”human in the loop

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:29:55.202558Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 339e9d24-e2e9-4b75-81ec-740c43044e29 · outbound

This paper cites From object transition to rce in the chrome renderer,.

A Systematization of Security Vulnerabilities in Computer Use Agents From object transition to rce in the chrome renderer,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:29:54.916401Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 92b5b938-5ae6-4d55-9d23-57d54fcf9108 · outbound

This paper cites Announcing the responses api and computer using agent in azure ai foundry,.

A Systematization of Security Vulnerabilities in Computer Use Agents Announcing the responses api and computer using agent in azure ai foundry,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:29:54.660640Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Pith citing papers

Observation 1eabc1c6-2842-458f-aa59-1c8aaf26e4a1 · inbound

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

Mind the Gap: Action Rebinding Attacks against Android GUI Agents A Systematization of Security Vulnerabilities in Computer Use Agents

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-03T09:54:57.493112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21cc77c1-16e6-4650-ab73-9dd794afba19 · inbound

Securing Computer-Use Agents: A Unified Architecture-Lifecycle Framework for Deployment-Grounded Reliability cites this paper.

Securing Computer-Use Agents: A Unified Architecture-Lifecycle Framework for Deployment-Grounded Reliability A Systematization of Security Vulnerabilities in Computer Use Agents

Reference 153

Resolution: verified exact; arxiv_id, observed 2026-05-11T04:35:55.938663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 669e3427-683f-4b85-9a42-cb778c125cd9 · inbound

Domain-Conditioned Safety in Frontier Computer-Using Agents: A 793-Episode Browser Benchmark, a Coding-Domain Cross-Reference, and a Reproducibility Audit of Recent Red-Teaming cites this paper.

Domain-Conditioned Safety in Frontier Computer-Using Agents: A 793-Episode Browser Benchmark, a Coding-Domain Cross-Reference, and a Reproducibility Audit of Recent Red-Teaming A Systematization of Security Vulnerabilities in Computer Use Agents

Reference 7

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T08:06:48.215369Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation efbdd2d8-8a16-4267-99db-810cf7ae5262 · inbound

Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation cites this paper.

Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation A Systematization of Security Vulnerabilities in Computer Use Agents

Reference 82

Resolution: verified exact; arxiv_id, observed 2026-06-27T13:20:57.086752Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.