Paper Citation Record · LEDGER

Imprompter: Tricking LLM Agents into Improper Tool Use

As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 26 inbound Pith citation observations for arXiv:2410.14923.

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

pith.paper-citation-record.v1
2410.14923 v2

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 26 of 26 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 26 of 26 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:37:51.603999Z

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

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

2
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 66e6083f-e437-47c3-874b-88c06a6b83e7 · inbound

Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions cites this paper.

Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions Imprompter: Tricking LLM Agents into Improper Tool Use

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-13T09:02:40.411688Z

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 aab7e631-2d14-4b0c-921c-5c3990c973cf · inbound

Lessons from Defending Gemini Against Indirect Prompt Injections cites this paper.

Lessons from Defending Gemini Against Indirect Prompt Injections Imprompter: Tricking LLM Agents into Improper Tool Use

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-07T15:37:51.603999Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac2626e6-3ed5-47fa-8f37-4d423204ba59 · inbound

Data-Centric Safety and Ethical Measures for Data and AI Governance cites this paper.

Data-Centric Safety and Ethical Measures for Data and AI Governance Imprompter: Tricking LLM Agents into Improper Tool Use

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T04:34:08.000242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87ea844c-4b84-4efe-b22f-b0f8cc12c09b · inbound

We Should Identify and Mitigate Third-Party Safety Risks in MCP-Powered Agent Systems cites this paper.

We Should Identify and Mitigate Third-Party Safety Risks in MCP-Powered Agent Systems Imprompter: Tricking LLM Agents into Improper Tool Use

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T00:32:36.507283Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef7e3098-7e36-4660-b5c1-1aa73879559b · inbound

FaSTA$^*$: Fast-Slow Toolpath Agent with Subroutine Mining for Efficient Multi-turn Image Editing cites this paper.

FaSTA$^*$: Fast-Slow Toolpath Agent with Subroutine Mining for Efficient Multi-turn Image Editing Imprompter: Tricking LLM Agents into Improper Tool Use

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-19T08:17:10.746601Z

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 b8580e78-b2fc-44d8-ad47-fd96cdb4f583 · 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 Imprompter: Tricking LLM Agents into Improper Tool Use

Reference 122

Resolution: unresolved; no resolver link, observed 2026-08-06T21:34:45.093922Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 757c4528-ba1f-4594-9e0b-f07bfcbb87e9 · inbound

Manipulating LLM Web Agents with Indirect Prompt Injection Attack via HTML Accessibility Tree cites this paper.

Manipulating LLM Web Agents with Indirect Prompt Injection Attack via HTML Accessibility Tree Imprompter: Tricking LLM Agents into Improper Tool Use

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-06T15:52:56.510579Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a7c8dd4-d55a-448e-aa63-0896643f70a5 · inbound

On the Future of Software Reuse in the Era of AI Native Software Engineering cites this paper.

On the Future of Software Reuse in the Era of AI Native Software Engineering Imprompter: Tricking LLM Agents into Improper Tool Use

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-05T15:29:05.783421Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc60bca4-8180-45eb-ab43-56784df000e4 · inbound

AgentSentinel: An End-to-End and Real-Time Security Defense Framework for Computer-Use Agents cites this paper.

AgentSentinel: An End-to-End and Real-Time Security Defense Framework for Computer-Use Agents Imprompter: Tricking LLM Agents into Improper Tool Use

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T21:44:12.278474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02c1bb54-0bef-4954-b47c-dde9e019eabb · inbound

AgentBound: Securing Execution Boundaries of AI Agents cites this paper.

AgentBound: Securing Execution Boundaries of AI Agents Imprompter: Tricking LLM Agents into Improper Tool Use

Reference 14

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T05:15:54.156005Z

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 8fae375b-c2cf-4058-b1bf-1bed57620730 · inbound

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

Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges Imprompter: Tricking LLM Agents into Improper Tool Use

Reference 45

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T03:42:22.516285Z

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 2f4b6a39-39f6-49ec-80b1-3cfe183eaf56 · 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 Imprompter: Tricking LLM Agents into Improper Tool Use

Reference 56

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T11:32:48.257431Z

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 5d05004d-b4bb-4c5f-ad2c-0db093425c95 · inbound

Security Threat Modeling for Emerging AI-Agent Protocols: A Comparative Analysis of MCP, A2A, Agora, and ANP cites this paper.

Security Threat Modeling for Emerging AI-Agent Protocols: A Comparative Analysis of MCP, A2A, Agora, and ANP Imprompter: Tricking LLM Agents into Improper Tool Use

Reference 71

Resolution: verified exact; arxiv_id, observed 2026-05-16T05:07:20.812637Z

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 fe22c24f-fdc2-4fff-94a8-7539659ed8de · inbound

From Storage to Steering: Memory Control Flow Attacks on LLM Agents cites this paper.

From Storage to Steering: Memory Control Flow Attacks on LLM Agents Imprompter: Tricking LLM Agents into Improper Tool Use

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-14T20:40:43.875392Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f631d8a7-2d9a-4229-aa2a-57fef3addcd8 · inbound

How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study cites this paper.

How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study Imprompter: Tricking LLM Agents into Improper Tool Use

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-13T19:53:11.688398Z

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 1fe5a63e-6a84-41a7-bcfe-92c99bfd40c2 · inbound

HarmfulSkillBench: How Do Harmful Skills Weaponize Your Agents? cites this paper.

HarmfulSkillBench: How Do Harmful Skills Weaponize Your Agents? Imprompter: Tricking LLM Agents into Improper Tool Use

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-10T10:34:29.224645Z

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 bb9e389e-d419-4939-bb20-1b698435fbbf · inbound

WARD: Adversarially Robust Defense of Web Agents Against Prompt Injections cites this paper.

WARD: Adversarially Robust Defense of Web Agents Against Prompt Injections Imprompter: Tricking LLM Agents into Improper Tool Use

Reference 21

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T14:45:49.558073Z

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 432be1f4-7116-4eb1-a1ec-aeef85c35e84 · inbound

Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety cites this paper.

Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety Imprompter: Tricking LLM Agents into Improper Tool Use

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-22T05:51:07.946360Z

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 f4c8e78c-002a-4c01-bf51-b6d2680fb3ee · inbound

Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety cites this paper.

Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety Imprompter: Tricking LLM Agents into Improper Tool Use

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-25T06:06:43.046681Z

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 a32cd385-442e-4221-ae45-5eeb7ecd29dd · inbound

"I Strongly Suspect This Website Is a Scam": Benchmarking PII Leakage and Detection without Defense in Autonomous Web Agents cites this paper.

"I Strongly Suspect This Website Is a Scam": Benchmarking PII Leakage and Detection without Defense in Autonomous Web Agents Imprompter: Tricking LLM Agents into Improper Tool Use

Reference 127

Resolution: verified exact; arxiv_id, observed 2026-06-28T19:42:36.161487Z

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 79b665f1-26d8-4d01-bda8-fcab0f5f660b · inbound

Assessing Automated Prompt Injection Attacks in Agentic Environments cites this paper.

Assessing Automated Prompt Injection Attacks in Agentic Environments Imprompter: Tricking LLM Agents into Improper Tool Use

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-07-03T06:17:41.981522Z

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 5486ad3f-d5bb-4798-af87-ff92b493f921 · inbound

SAIGuard: Communication-State Simulation for Proactive Defense of LLM Multi-Agent Systems cites this paper.

SAIGuard: Communication-State Simulation for Proactive Defense of LLM Multi-Agent Systems Imprompter: Tricking LLM Agents into Improper Tool Use

Reference 17

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T13:28:18.842251Z

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 8a2bfdbd-ac6d-49fe-a55a-265fd27b1e89 · inbound

AutoDojo: Adaptive Black-Box Attacks Reveal the Limits of IPI Defenses and Task-Specification Effects in LLM Agents cites this paper.

AutoDojo: Adaptive Black-Box Attacks Reveal the Limits of IPI Defenses and Task-Specification Effects in LLM Agents Imprompter: Tricking LLM Agents into Improper Tool Use

Reference 42

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T16:48:40.495135Z

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 c52f5f5f-d966-4c28-9e05-07c50195f8c3 · inbound

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

DualView: Preventing Indirect Prompt Injection in Personal AI Agents Imprompter: Tricking LLM Agents into Improper Tool Use

Reference 58

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 aa3314d3-c3fa-4027-98e2-0b3b8e754aea · inbound

Agent Data Injection Attacks are Realistic Threats to AI Agents cites this paper.

Agent Data Injection Attacks are Realistic Threats to AI Agents Imprompter: Tricking LLM Agents into Improper Tool Use

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-11T08:31:36.099368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61022b50-8da0-46cb-85f6-ca54b0432b68 · inbound

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

Agent Security Needs Redefinition through a Holistic Framework Imprompter: Tricking LLM Agents into Improper Tool Use

Reference 269

Resolution: unresolved; no resolver link, observed 2026-08-01T06:04:46.607188Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.