Paper Citation Record · LEDGER

Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents

As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 16 inbound Pith citation observations for arXiv:2410.13886.

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

pith.paper-citation-record.v1
2410.13886 v2

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 16 of 16 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 16 of 16 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T00:15:01.139782Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-02T08:06:48.241191Z

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 1f5deb70-d016-4da3-993c-b3740f09e8d6 · inbound

Humanity's Last Exam cites this paper.

Humanity's Last Exam Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-10T18:40:50.378768Z

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 8b52a7d5-405b-487e-8c8d-cc4f842f5f41 · inbound

A Survey on the Safety and Security Threats of Computer-Using Agents: JARVIS or Ultron? cites this paper.

A Survey on the Safety and Security Threats of Computer-Using Agents: JARVIS or Ultron? Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-22T15:24:57.839929Z

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 8790198c-cfc5-4bb9-84bc-f284d8110a6b · inbound

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety cites this paper.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:01.139782Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ab7792c-e789-4154-a3b6-519601f1212d · inbound

Context manipulation attacks : Web agents are susceptible to corrupted memory cites this paper.

Context manipulation attacks : Web agents are susceptible to corrupted memory Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T23:59:57.578866Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5d4f524-359c-4948-a729-9195ce0ab1da · 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 Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-06T21:34:43.602465Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation caddabb4-294c-48d2-b1e5-78e4f70d6b39 · inbound

LLMs are Capable of Misaligned Behavior Under Explicit Prohibition and Surveillance cites this paper.

LLMs are Capable of Misaligned Behavior Under Explicit Prohibition and Surveillance Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T21:22:59.013316Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d841a2f-ec22-4551-9981-9270bd8ee601 · inbound

SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents cites this paper.

SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-18T08:16:06.580695Z

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 dc631708-1152-4254-a5d9-e407302c48c9 · inbound

The Social Cost of Intelligence: Emergence, Propagation, and Amplification of Stereotypical Bias in Multi-Agent Systems cites this paper.

The Social Cost of Intelligence: Emergence, Propagation, and Amplification of Stereotypical Bias in Multi-Agent Systems Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T10:16:02.320578Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c50f0a73-6ec3-451d-93d6-fc8011508c09 · inbound

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels cites this paper.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.033013Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f57a6247-9876-4af1-8268-35de4ccb737b · inbound

The 2025 AI Agent Index: Documenting Technical and Safety Features of Deployed Agentic AI Systems cites this paper.

The 2025 AI Agent Index: Documenting Technical and Safety Features of Deployed Agentic AI Systems Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents

Reference 77

Resolution: verified exact; arxiv_id, observed 2026-05-15T20:46:36.186400Z

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 d7802825-59ec-4bb1-9b3c-187c789e5b4f · inbound

AgentWorm: Self-Propagating Attacks Across LLM Agent Ecosystems cites this paper.

AgentWorm: Self-Propagating Attacks Across LLM Agent Ecosystems Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-02T18:10:38.060471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38f9d78d-96bd-4d95-a5fc-19938868ad31 · inbound

Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw cites this paper.

Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents

Reference 8

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T23:05:49.008995Z

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 cc48aef2-9002-442e-b1c0-0a439ee6f23e · 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 Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents

Reference 9

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T08:06:48.242777Z

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 a428daee-0475-4eda-9ca2-16350193fbf6 · inbound

Refused in Chat, Written in Code: Workflow-Level Jailbreak Construction in IDE Coding Agents cites this paper.

Refused in Chat, Written in Code: Workflow-Level Jailbreak Construction in IDE Coding Agents Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-11T22:40:37.839133Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e38be30-be24-4324-9734-978f2d789f73 · inbound

Refused in Chat, Written in Code: Workflow-Level Jailbreak Construction in IDE Coding Agents cites this paper.

Refused in Chat, Written in Code: Workflow-Level Jailbreak Construction in IDE Coding Agents Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-13T07:01:49.222325Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06c5071e-9eaf-4bc1-8498-5c5b9cf01bf6 · inbound

ToolAlignBench: Investigating Alignment Conflicts in Tool-Calling Enabled LLMs cites this paper.

ToolAlignBench: Investigating Alignment Conflicts in Tool-Calling Enabled LLMs Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-02T02:35:37.029971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.