Paper Citation Record · LEDGER

Design Patterns for Securing LLM Agents against Prompt Injections

As of 4 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 32 inbound Pith citation observations for arXiv:2506.08837.

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

pith.paper-citation-record.v1
2506.08837 v3

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 32 of 32 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-04T06:34:03.388597+00:00

measured 32 of 32 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T08:06:09.223677Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-10T12:27:04.097770Z

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 3035d91c-4bf4-4a01-b1b6-44cd415829a1 · inbound

Prompt Injection Attack to Tool Selection in LLM Agents cites this paper.

Prompt Injection Attack to Tool Selection in LLM Agents Design Patterns for Securing LLM Agents against Prompt Injections

Reference 73

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T17:08:29.063576Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 557428b5-3b14-4f23-8503-e7b4b2f00627 · inbound

When Compression Becomes an Attack Surface: Black-Box Attacks on Prompt-Compressed LLM Agents cites this paper.

When Compression Becomes an Attack Surface: Black-Box Attacks on Prompt-Compressed LLM Agents Design Patterns for Securing LLM Agents against Prompt Injections

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T08:06:09.223677Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 421e278b-f1e9-433b-a767-52f1e0f20db0 · inbound

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

Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges Design Patterns for Securing LLM Agents against Prompt Injections

Reference 59

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T03:42:22.528614Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ca0e399b-891b-47bc-8350-aca7d93946ee · inbound

Prevalence of Security and Privacy Risk-Inducing Usage of AI-based Conversational Agents cites this paper.

Prevalence of Security and Privacy Risk-Inducing Usage of AI-based Conversational Agents Design Patterns for Securing LLM Agents against Prompt Injections

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T07:01:14.483509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fcd2aeea-d216-45cd-9b46-e6ef4820eb08 · 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 Design Patterns for Securing LLM Agents against Prompt Injections

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-22T12:51:33.451649Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 349bed18-f6e7-40a0-865b-88bc47d9813f · inbound

Tracking Capabilities for Safer Agents cites this paper.

Tracking Capabilities for Safer Agents Design Patterns for Securing LLM Agents against Prompt Injections

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-15T18:36:29.247485Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f47ad6d8-a9d1-4e8f-9fd3-bd17c9c387a4 · inbound

LogJack: Indirect Prompt Injection Through Cloud Logs Against LLM Debugging Agents cites this paper.

LogJack: Indirect Prompt Injection Through Cloud Logs Against LLM Debugging Agents Design Patterns for Securing LLM Agents against Prompt Injections

Reference 1

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T13:55:29.084211Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation bbefcaaa-25ed-46d3-8971-260da12cc5e5 · inbound

Alignment Contracts for Agentic Security Systems cites this paper.

Alignment Contracts for Agentic Security Systems Design Patterns for Securing LLM Agents against Prompt Injections

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-11T15:01:04.910407Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d3f339d7-4ece-4549-8ea7-e862d4488316 · inbound

Trojan Hippo: Weaponizing Agent Memory for Data Exfiltration cites this paper.

Trojan Hippo: Weaponizing Agent Memory for Data Exfiltration Design Patterns for Securing LLM Agents against Prompt Injections

Reference 6

Resolution: metadata mismatch; arxiv_id, observed 2026-05-19T17:32:41.588564Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation fbe41ca5-0fc7-48cf-935c-9ebc11b9416d · inbound

IPI-proxy: An Intercepting Proxy for Red-Teaming Web-Browsing AI Agents Against Indirect Prompt Injection cites this paper.

IPI-proxy: An Intercepting Proxy for Red-Teaming Web-Browsing AI Agents Against Indirect Prompt Injection Design Patterns for Securing LLM Agents against Prompt Injections

Reference 19

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T05:47:21.309927Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 89d9bc78-ec48-46d0-b108-58bea1a2e519 · inbound

Web Agents Should Adopt the Plan-Then-Execute Paradigm cites this paper.

Web Agents Should Adopt the Plan-Then-Execute Paradigm Design Patterns for Securing LLM Agents against Prompt Injections

Reference 3

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T02:43:33.372927Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 6a4a398c-ba3c-4d78-baae-139ba393d87d · inbound

The Insurability Frontier of AI Risk: Mapping Threats to Affirmative Coverage, Silent Exposures, and Exclusions cites this paper.

The Insurability Frontier of AI Risk: Mapping Threats to Affirmative Coverage, Silent Exposures, and Exclusions Design Patterns for Securing LLM Agents against Prompt Injections

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-20T23:33:50.920592Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ffd7a805-ebec-4f09-9b6c-9e37d5f969bc · inbound

Agentic-J: An AI Agent for Biological Microscopy Image Analysis cites this paper.

Agentic-J: An AI Agent for Biological Microscopy Image Analysis Design Patterns for Securing LLM Agents against Prompt Injections

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-07-02T01:36:25.311723Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation fed40526-eb57-4b76-8c65-afe923f74566 · inbound

What You Approve Is What Executes: Consent Integrity for Black-Box LLM Agents cites this paper.

What You Approve Is What Executes: Consent Integrity for Black-Box LLM Agents Design Patterns for Securing LLM Agents against Prompt Injections

Reference 18

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T23:36:22.921717Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 529405dc-6e36-4f9c-b92c-19ed75aaf16e · inbound

Data Flow Control: Data Safety Policies for AI Agents cites this paper.

Data Flow Control: Data Safety Policies for AI Agents Design Patterns for Securing LLM Agents against Prompt Injections

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-07-02T15:47:06.357233Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 8a55b5ac-366f-45b3-a23c-3a2fafee5c79 · inbound

Game-Theoretic Multi-Agent Control for Robust Contextual Reasoning in LLMs cites this paper.

Game-Theoretic Multi-Agent Control for Robust Contextual Reasoning in LLMs Design Patterns for Securing LLM Agents against Prompt Injections

Reference 22

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T05:47:41.197854Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d22383bd-4dfc-4893-ba75-e1253cb95ee9 · inbound

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

Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation Design Patterns for Securing LLM Agents against Prompt Injections

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-06-27T13:20:57.094470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 175a722a-4c15-427e-a3a4-068bbe2d7335 · inbound

Lingering Authority: Revocable Resource-and-Effect Capabilities for Coding Agents cites this paper.

Lingering Authority: Revocable Resource-and-Effect Capabilities for Coding Agents Design Patterns for Securing LLM Agents against Prompt Injections

Reference 5

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T09:19:43.605487Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b459f59e-ff63-4e41-8a1d-357c3c82495c · inbound

GIF: Locally Sound Geometric Information Flow Control for LLMs cites this paper.

GIF: Locally Sound Geometric Information Flow Control for LLMs Design Patterns for Securing LLM Agents against Prompt Injections

Reference 13

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T10:49:46.741547Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 7dcc35be-7d05-4c3f-9094-c9f53153b919 · inbound

Adaptive Evaluation of Out-of-Band Defenses Against Prompt Injection in LLM Agents cites this paper.

Adaptive Evaluation of Out-of-Band Defenses Against Prompt Injection in LLM Agents Design Patterns for Securing LLM Agents against Prompt Injections

Reference 23

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T13:39:51.328735Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 808a4815-8a81-4ea8-9eaf-80a9b706cf7f · inbound

Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents cites this paper.

Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents Design Patterns for Securing LLM Agents against Prompt Injections

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-07-04T14:09:53.262547Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 2f4644b6-c99c-416d-b7c3-1d0252e42811 · inbound

Janus: a Playground for User-Involved Agentic Permission Management cites this paper.

Janus: a Playground for User-Involved Agentic Permission Management Design Patterns for Securing LLM Agents against Prompt Injections

Reference 2

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T20:08:54.778632Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a45d9e9d-2c75-464b-8052-b1b799c2e4ff · inbound

Beyond Self-Resolution: Settlement Factorization for Robust Natural Language Mechanism cites this paper.

Beyond Self-Resolution: Settlement Factorization for Robust Natural Language Mechanism Design Patterns for Securing LLM Agents against Prompt Injections

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-11T19:34:52.611804Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9eb4f866-d0b6-498b-bfa0-d98b81f35732 · inbound

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

Agent Data Injection Attacks are Realistic Threats to AI Agents Design Patterns for Securing LLM Agents against Prompt Injections

Reference 37

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 bfd5d8d7-340e-4927-ae45-9a02af7cf509 · inbound

Prismata: Confining Cross-Site Prompt Injection in Web Agents cites this paper.

Prismata: Confining Cross-Site Prompt Injection in Web Agents Design Patterns for Securing LLM Agents against Prompt Injections

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-07-10T12:27:04.099528Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ecb94da7-7e5f-41c0-91a9-11c532e3b281 · inbound

Adversarial Prompting Framework for AI Safety Assessment cites this paper.

Adversarial Prompting Framework for AI Safety Assessment Design Patterns for Securing LLM Agents against Prompt Injections

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T05:10:09.289891Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f09d9082-5519-4344-9b07-828395f81160 · inbound

Specifying the Delegated-Autonomy Boundary: Requirements Engineering for Agentic AI cites this paper.

Specifying the Delegated-Autonomy Boundary: Requirements Engineering for Agentic AI Design Patterns for Securing LLM Agents against Prompt Injections

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T18:40:55.397024Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77f03a05-7c8b-4407-a4f2-162945b4802f · inbound

IssueTrojanBench: Benchmarking AI Coding Agents Against Malicious Issue Requests cites this paper.

IssueTrojanBench: Benchmarking AI Coding Agents Against Malicious Issue Requests Design Patterns for Securing LLM Agents against Prompt Injections

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-01T09:30:52.016053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b169d889-a5d9-4a70-a222-129b8d5ea01f · inbound

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

Agent Security Needs Redefinition through a Holistic Framework Design Patterns for Securing LLM Agents against Prompt Injections

Reference 197

Resolution: unresolved; no resolver link, observed 2026-08-01T06:04:46.261016Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a235574-ca91-4afd-836c-fa9a52b7f157 · inbound

Are You Still the Agent I Authorized? Earned Authority under a Fixed Ceiling for Evolving Agents cites this paper.

Are You Still the Agent I Authorized? Earned Authority under a Fixed Ceiling for Evolving Agents Design Patterns for Securing LLM Agents against Prompt Injections

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-30T18:16:45.183096Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77238753-6243-414d-9a2a-f05a02807625 · inbound

How Context Attribution Handles What the Model Already Knows cites this paper.

How Context Attribution Handles What the Model Already Knows Design Patterns for Securing LLM Agents against Prompt Injections

Reference 54

Resolution: unresolved; no resolver link, observed 2026-07-30T12:03:18.274762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 372f391f-490e-4885-a115-6d34b9a4b96a · inbound

AISPA: User-Centric System Prompt Auditing for Large Language Model Applications cites this paper.

AISPA: User-Centric System Prompt Auditing for Large Language Model Applications Design Patterns for Securing LLM Agents against Prompt Injections

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-07-31T02:04:06.710922Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.