Paper Citation Record · LEDGER

The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents

As of 11 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 13 inbound Pith citation observations for arXiv:2412.16682.

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

pith.paper-citation-record.v1
2412.16682 v1

Coverage vector

measured 38 of 38 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T10:24:27.048790Z

measured 51 of 51 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-11T06:34:44.6726+00:00

measured 13 of 13 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:55:01.117692Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T16:58:43.565621Z

Reference resolution

38 of 38 outbound references displayed

verified exact2
verified fuzzy1
unresolved35
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation bcf99d7c-016a-465b-b6a2-abde8f1a0ebf · outbound

This paper cites online" 'onlinestring :=.

The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents online" 'onlinestring :=

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-11T10:24:26.757134Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d93e7f28-cce8-4484-8ec3-5fa9af4ee8b3 · outbound

This paper cites write newline.

The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents write newline

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-11T10:24:26.762707Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea47b1c7-24b8-4abb-90f2-2016884e6940 · outbound

This paper cites an unresolved cited work.

The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-08-11T10:24:27.805648Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 484e8516-d9db-4fbd-96ea-2ececb9cd542 · outbound

This paper cites StruQ: Defending Against Prompt Injection with Structured Queries.

The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents StruQ: Defending Against Prompt Injection with Structured Queries

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-11T10:24:26.774479Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76a685bd-7663-4b7f-b311-84a73ec55477 · outbound

This paper cites AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents.

The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-11T10:24:26.779495Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b6a45ef-dd91-41d8-8544-dea7e7acb896 · outbound

This paper cites an unresolved cited work.

The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents Unresolved cited work

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-11T10:24:26.784475Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17d38585-9607-462f-8001-04814cf78fb6 · outbound

This paper cites an unresolved cited work.

The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-08-11T10:24:27.783322Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation d2c0925e-10e3-4ba1-a904-89ee26259d3e · outbound

This paper cites an unresolved cited work.

The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents Unresolved cited work

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T10:24:26.793700Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df98e536-0949-4705-b6bc-dbe534cd74d0 · outbound

This paper cites Gupta, Niloofar Mireshghallah, Taylor Berg-Kirkpatrick, and Earlence Fernandes.

The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents Gupta, Niloofar Mireshghallah, Taylor Berg-Kirkpatrick, and Earlence Fernandes

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T10:24:27.768749Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 94c3276b-a666-4d26-874f-525a1df8a0b2 · outbound

This paper cites an unresolved cited work.

The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents Unresolved cited work

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T10:24:26.803006Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3acd4214-4126-4989-98aa-89fc8f5aace1 · outbound

This paper cites an unresolved cited work.

The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents Unresolved cited work

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-11T10:24:26.807345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71c654a6-5307-4ad3-a490-f176f40a7b23 · outbound

This paper cites Defending Against Indirect Prompt Injection Attacks With Spotlighting.

The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents Defending Against Indirect Prompt Injection Attacks With Spotlighting

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-11T10:24:26.933542Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bc17b03-a4cb-4959-a64c-72f72af03d4f · outbound

This paper cites Recommender AI Agent: Integrating Large Language Models for Interactive Recommendations.

The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents Recommender AI Agent: Integrating Large Language Models for Interactive Recommendations

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T10:24:26.937799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6560390-5104-41cf-abbd-bcaa6a2448c5 · outbound

This paper cites Palisade -- Prompt Injection Detection Framework.

The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents Palisade -- Prompt Injection Detection Framework

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-08-11T10:24:27.330478Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 3f040989-1353-46fc-8b8f-160540a97800 · outbound

This paper cites Whom to Trust? Elective Learning for Distributed Gaussian Process Regression.

The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents Whom to Trust? Elective Learning for Distributed Gaussian Process Regression

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-08-11T10:24:27.308043Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation cfd0bb1c-cbae-4a4b-88d2-a9b016e901dd · outbound

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

The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents Prompt Injection attack against LLM-integrated Applications

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-11T10:24:26.952239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65e2677d-278b-4aef-8373-35f3e37dde80 · outbound

This paper cites an unresolved cited work.

The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-11T10:24:27.744602Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation ee2b5907-d90b-4b39-b78b-a01cdc9f2b8a · outbound

This paper cites an unresolved cited work.

The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents Unresolved cited work

Reference 19

Resolution: unresolved; raw_fallback, observed 2026-08-11T10:24:27.729799Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 6a7f2124-6096-4d18-90ca-e2a2afef1ffa · outbound

This paper cites an unresolved cited work.

The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents Unresolved cited work

Reference 20

Resolution: unresolved; raw_fallback, observed 2026-08-11T10:24:27.715161Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation a34672dd-4f90-4939-86b7-59ed44be8df7 · outbound

This paper cites an unresolved cited work.

The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents Unresolved cited work

Reference 21

Resolution: unresolved; raw_fallback, observed 2026-08-11T10:24:27.701052Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 5f6c73d7-a0bb-442a-ada1-117515891602 · outbound

This paper cites an unresolved cited work.

The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents Unresolved cited work

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-11T10:24:26.972102Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36386400-ab38-442b-b3e9-6cc1530b7097 · outbound

This paper cites Gorilla: Large Language Model Connected with Massive APIs.

The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents Gorilla: Large Language Model Connected with Massive APIs

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-11T10:24:26.975809Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa91ded2-6669-44ff-9d59-e17902d476c8 · outbound

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

The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents Ignore Previous Prompt: Attack Techniques For Language Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-11T10:24:26.979697Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 746e4891-1d42-4be8-8177-c845af83407e · outbound

This paper cites Jatmo: Prompt Injection Defense by Task-Specific Finetuning.

The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents Jatmo: Prompt Injection Defense by Task-Specific Finetuning

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-11T10:24:26.983523Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf6a7214-f7d6-44f4-898f-053be29809e6 · outbound

This paper cites an unresolved cited work.

The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-08-11T10:24:27.677129Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 56d2b729-8275-4768-b4b9-341bb4a6f248 · outbound

This paper cites ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs.

The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-11T10:24:26.992471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79913162-26e2-469c-8b01-b941dc1a52bf · outbound

This paper cites an unresolved cited work.

The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents Unresolved cited work

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-11T10:24:26.997239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ac53856-199a-472b-84e5-3a53171bb034 · outbound

This paper cites an unresolved cited work.

The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-08-11T10:24:27.652442Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation db738dc8-08bb-4e65-a7b9-132119b530d8 · outbound

This paper cites ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases.

The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-11T10:24:27.006328Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72f79fa5-3b0f-41fe-82ff-65ea438f2905 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-11T10:24:27.011050Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dcc648a0-67f7-4a86-9803-ebf7a875a12f · outbound

This paper cites The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions.

The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-11T10:24:27.016077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6bf1c9c8-fa8b-4ae4-afea-1f963c6ab16d · outbound

This paper cites FATH: Authentication-based Test-time Defense against Indirect Prompt Injection Attacks.

The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents FATH: Authentication-based Test-time Defense against Indirect Prompt Injection Attacks

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-11T10:24:27.020630Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 925909bd-96d6-4f78-814d-59dfd0e55d5d · outbound

This paper cites Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models.

The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-11T10:24:27.025077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbe276cd-bc22-4a66-a1cd-42eccb588a63 · outbound

This paper cites Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy.

The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-11T10:24:27.030118Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55a100af-990e-4bbc-b180-2afb7374885a · outbound

This paper cites GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning.

The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-11T10:24:27.034983Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c845cf5-c9c7-4bbb-9a99-e69d44e5aae2 · outbound

This paper cites an unresolved cited work.

The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents Unresolved cited work

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-11T10:24:27.039647Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 968de845-c1d1-46e8-b04c-6436f9478028 · outbound

This paper cites InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents.

The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-11T10:24:27.044054Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation caf73733-d20f-40e8-8442-d013003c7282 · outbound

This paper cites RepViT: Revisiting Mobile CNN From ViT Perspective.

The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents RepViT: Revisiting Mobile CNN From ViT Perspective

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-11T10:24:27.048790Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 7c6505b0-d9e2-4deb-afc8-d38971922780 · inbound

Large Language Model Agent: A Survey on Methodology, Applications and Challenges cites this paper.

Large Language Model Agent: A Survey on Methodology, Applications and Challenges The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents

Reference 209

Resolution: verified exact; arxiv_id, observed 2026-05-22T21:52:10.110882Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation a24a8668-3f8e-4800-b980-9aad03164431 · inbound

Invisible Prompts, Visible Threats: Malicious Font Injection in External Resources for Large Language Models cites this paper.

Invisible Prompts, Visible Threats: Malicious Font Injection in External Resources for Large Language Models The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T14:55:01.117692Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f61e6893-03d9-438a-b98e-1c47a1604f0f · inbound

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

Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents

Reference 202

Resolution: verified exact; arxiv_id, observed 2026-05-18T03:42:22.422809Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 602dcf49-7c87-4618-aee3-8e8aa34947ed · inbound

The LLMbda Calculus: AI Agents, Conversations, and Information Flow cites this paper.

The LLMbda Calculus: AI Agents, Conversations, and Information Flow The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-02T21:31:24.539379Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5dfe640-3403-4a92-88f1-f6a84b0f2533 · inbound

CapSeal: Capability-Sealed Secret Mediation for Secure Agent Execution cites this paper.

CapSeal: Capability-Sealed Secret Mediation for Secure Agent Execution The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-10T07:52:13.816090Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 39f11dd9-3835-454e-9e1f-23ecd168e821 · inbound

AgentShield: Deception-based Compromise Detection for Tool-using LLM Agents cites this paper.

AgentShield: Deception-based Compromise Detection for Tool-using LLM Agents The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-13T01:32:02.665345Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation ae4b724b-a685-4486-a15a-d71460f0ac21 · inbound

No More, No Less: Task Alignment in Terminal Agents cites this paper.

No More, No Less: Task Alignment in Terminal Agents The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:57:22.412603Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 16d9ff76-c4db-40cd-8254-d77fbc15726d · inbound

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

Web Agents Should Adopt the Plan-Then-Execute Paradigm The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-15T02:43:33.427337Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation a6441a34-ccbf-405e-8d1a-f9ffdf08b84e · 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 The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-07-03T05:47:41.182833Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation b97fe467-b2be-45b0-a54e-1ecf87f86479 · inbound

From Shield to Target: Denial-of-Service Attacks on LLM-Based Agent Guardrails cites this paper.

From Shield to Target: Denial-of-Service Attacks on LLM-Based Agent Guardrails The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-07-03T16:58:43.567273Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation a937b614-d959-4866-b85a-e7f590837ba4 · inbound

MOSAIC: Knowledge-Guided CLI Command Composition Attack in LLM Coding Agents cites this paper.

MOSAIC: Knowledge-Guided CLI Command Composition Attack in LLM Coding Agents The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents

Reference 40

Resolution: unresolved; no resolver link, observed 2026-07-12T06:34:07.307906Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 464c419e-90e4-4deb-995a-229b9da82332 · inbound

RT-SHCUA: Real-Time Self-Hosted Computer-Use Agent for UAV Control cites this paper.

RT-SHCUA: Real-Time Self-Hosted Computer-Use Agent for UAV Control The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-01T16:35:19.137603Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1847c81d-a1bd-4925-8204-fb4336c41cec · inbound

ContainmentBench: Trace-Based Evaluation of Post-Injection Containment in Tool-Using LLM Agents cites this paper.

ContainmentBench: Trace-Based Evaluation of Post-Injection Containment in Tool-Using LLM Agents The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-31T23:24:19.538321Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.