Paper Citation Record · LEDGER

Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents

As of 22 August 2026, this Paper Citation Record lists 36 of 36 outbound references and 0 inbound Pith citation observations for arXiv:2607.19837.

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

pith.paper-citation-record.v1
2607.19837 v1

Coverage vector

measured 36 of 36 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T11:38:21.167591Z

measured 36 of 36 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

36 of 36 outbound references displayed

verified exact0
verified fuzzy0
unresolved36
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 439a50fc-99b9-4e87-8b3e-ef0aa8567205 · outbound

This paper cites Toolformer: Language models can teach themselves to use tools,.

Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents Toolformer: Language models can teach themselves to use tools,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T11:38:17.724576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 406f13a8-d145-472d-abd3-0c4fea9fd29a · outbound

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

Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents ReAct: Synergizing Reasoning and Acting in Language Models

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-01T11:38:17.811439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3835fcb9-75e7-43d8-9357-b1e3b5998c37 · outbound

This paper cites Webarena: A realistic web environ- ment for building autonomous agents,.

Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents Webarena: A realistic web environ- ment for building autonomous agents,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-01T11:38:17.873374Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc5d88c4-e067-4ab8-a17b-266a9a27e4f4 · outbound

This paper cites Hug- ginggpt: Solving ai tasks with chatgpt and its friends in hugging face,.

Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents Hug- ginggpt: Solving ai tasks with chatgpt and its friends in hugging face,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-01T11:38:17.939940Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4324c514-e183-449d-85ee-2f56c0bfff77 · outbound

This paper cites Openhands: An open platform for ai software developers as generalist agents,.

Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents Openhands: An open platform for ai software developers as generalist agents,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T11:38:18.003418Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef692a33-3a5a-4d1e-8e4f-32f774fed009 · outbound

This paper cites Not what you’ve signed up for: Compromising real- world llm-integrated applications with indirect prompt injection,.

Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents Not what you’ve signed up for: Compromising real- world llm-integrated applications with indirect prompt injection,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T11:38:18.073366Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8224f54-7a93-4d77-907b-630c8fd2f9e3 · outbound

This paper cites OW ASP Top 10 for Large Language Model Applications,.

Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents OW ASP Top 10 for Large Language Model Applications,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T11:38:18.157562Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69c3665a-794d-4bbf-a3a7-5398b763c3f3 · outbound

This paper cites Prompt injection attacks against gpt-3,.

Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents Prompt injection attacks against gpt-3,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T11:38:18.279577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f285f95-910b-465d-acc6-52ad24d85793 · outbound

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

Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents Ignore Previous Prompt: Attack Techniques For Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T11:38:18.391594Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d34a9f1-220a-4668-9a11-9b2259266236 · outbound

This paper cites Agentvigil: Automatic black-box red-teaming for indirect prompt injection against llm agents,.

Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents Agentvigil: Automatic black-box red-teaming for indirect prompt injection against llm agents,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T11:38:18.505283Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24eae479-604f-4232-bf5d-39ced6fdad31 · outbound

This paper cites Topicattack: An indirect prompt injection attack via topic transition,.

Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents Topicattack: An indirect prompt injection attack via topic transition,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T11:38:18.597411Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1f18558-62f8-4566-9ddf-8fca0cd700df · outbound

This paper cites Agentx- ploit: End-to-end red-teaming for ai agents powdered by multi-agent systems.

Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents Agentx- ploit: End-to-end red-teaming for ai agents powdered by multi-agent systems

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T11:38:18.703530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d091e421-e7d3-4936-ab85-ce9eda9ccf9b · outbound

This paper cites Adaptools: Adaptive tool-based in- direct prompt injection attacks on agentic llms,.

Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents Adaptools: Adaptive tool-based in- direct prompt injection attacks on agentic llms,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T11:38:18.773275Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74d790ad-8cb5-4176-bda6-496a1c82b9f4 · outbound

This paper cites Security challenges in ai agent deployment: Insights from a large scale public competi- tion,.

Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents Security challenges in ai agent deployment: Insights from a large scale public competi- tion,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T11:38:18.917301Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16c1cd37-6130-40e8-95af-1498e1c15a93 · outbound

This paper cites "real attackers don’t compute gradients.

Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents "real attackers don’t compute gradients

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T11:38:18.974397Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 509b499f-e1b6-4b29-a5c4-111513f6c1fd · outbound

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

Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents Prompt Injection attack against LLM-integrated Applications

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T11:38:19.117826Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d7e5468-3fd0-4549-9d6d-d937b507e4f5 · outbound

This paper cites Agentdojo: A dynamic environment to evaluate prompt injection attacks and defenses for LLM agents,.

Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents Agentdojo: A dynamic environment to evaluate prompt injection attacks and defenses for LLM agents,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T11:38:19.156471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3b1ab49-46b0-4d2e-b6ef-2942b7526974 · outbound

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

Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T11:38:19.254094Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05a35f45-341e-4709-92d2-1921aee36735 · outbound

This paper cites ChatInject: Abusing Chat Templates for Prompt Injection in LLM Agents.

Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents ChatInject: Abusing Chat Templates for Prompt Injection in LLM Agents

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T11:38:19.374306Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 884ac497-cf9b-4395-bf92-330b86f12931 · outbound

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

Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents Prompt Injection Attack to Tool Selection in LLM Agents

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-01T11:38:19.451019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10044431-dfe8-496f-a514-cc53671bdb1a · outbound

This paper cites Obliinjection: Order-oblivious prompt injection attack to llm agents with multi-source data,.

Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents Obliinjection: Order-oblivious prompt injection attack to llm agents with multi-source data,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-01T11:38:19.527776Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b17e9f1-3daf-4a2b-ae26-da210751b368 · outbound

This paper cites AgentVigil: Generic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents.

Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents AgentVigil: Generic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-01T11:38:19.674889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d20f8c5-8837-485e-9eb0-d048eb27d4b3 · outbound

This paper cites Autohijacker: Automatic indirect prompt injection against black-box LLM agents,.

Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents Autohijacker: Automatic indirect prompt injection against black-box LLM agents,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-01T11:38:19.816027Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f47252f-d67d-4d46-8782-9986e52a8ca1 · outbound

This paper cites Agentxploit: End-to-end red-teaming for AI agents powdered by multi-agent systems,.

Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents Agentxploit: End-to-end red-teaming for AI agents powdered by multi-agent systems,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-01T11:38:19.894752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 974b7850-a8c9-4c18-9a0c-1e312a6b0300 · outbound

This paper cites Tooltweak: An attack on tool selection in llm-based agents,.

Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents Tooltweak: An attack on tool selection in llm-based agents,

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-01T11:38:19.997439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f16feac-0b42-4e09-95a7-4bc030cc665c · outbound

This paper cites Verigrey: Greybox agent validation,.

Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents Verigrey: Greybox agent validation,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-01T11:38:20.114753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00f2b1d0-3081-4e5a-bca5-0a832b70c9c2 · outbound

This paper cites SkillJect: Effectively Automating Skill-Based Prompt Injection for Skill-Enabled Agents.

Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents SkillJect: Effectively Automating Skill-Based Prompt Injection for Skill-Enabled Agents

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-01T11:38:20.224853Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f54a5ea-3e5e-4731-9dbf-5e8c0f3b8ecd · outbound

This paper cites Udora: A unified red teaming framework against llm agents by dynamically hijacking their own reasoning,.

Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents Udora: A unified red teaming framework against llm agents by dynamically hijacking their own reasoning,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-01T11:38:20.324753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 506ddbd4-b000-4ee3-b561-3aacd36afb6c · outbound

This paper cites Bench- marking and defending against indirect prompt injection attacks on large language models,.

Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents Bench- marking and defending against indirect prompt injection attacks on large language models,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-01T11:38:20.414827Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f29c388e-4120-4db7-8372-d5d81442e719 · outbound

This paper cites Agent security bench (asb): Formalizing and benchmark- ing attacks and defenses in llm-based agents,.

Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents Agent security bench (asb): Formalizing and benchmark- ing attacks and defenses in llm-based agents,

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-01T11:38:20.545074Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 617e5efd-51f7-4608-ba58-8137230741e6 · outbound

This paper cites Universal and Context-Independent Triggers for Precise Control of LLM Outputs.

Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents Universal and Context-Independent Triggers for Precise Control of LLM Outputs

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-01T11:38:20.754753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9df13c94-2b54-4595-8378-68e2012e0a89 · outbound

This paper cites Trojan’s whisper: Stealthy manipulation of openclaw through injected bootstrapped guidance,.

Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents Trojan’s whisper: Stealthy manipulation of openclaw through injected bootstrapped guidance,

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-01T11:38:20.844901Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c3c54a5-a722-4862-8002-5e1b296c0bc4 · outbound

This paper cites Openclaw docs,.

Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents Openclaw docs,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-01T11:38:20.934753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb9eb1ff-679c-4e82-b893-34f5e6c0727a · outbound

This paper cites Fine-tuned deberta-v3-base for prompt injection detection,.

Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents Fine-tuned deberta-v3-base for prompt injection detection,

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-01T11:38:21.054852Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a8d5faf-b4fd-4723-adea-a3a4f4635572 · outbound

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

Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents Defending Against Indirect Prompt Injection Attacks With Spotlighting

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-01T11:38:21.167591Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bf5d298-f643-4924-88c2-b4ec411cc881 · outbound

This paper cites "Real Attackers Don't Compute Gradients": Bridging the Gap Between Adversarial ML Research and Practice.

Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents "Real Attackers Don't Compute Gradients": Bridging the Gap Between Adversarial ML Research and Practice

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-01T11:38:19.047650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.