Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-06T05:11:49.315668Z
Paper Citation Record · LEDGER
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming
As of 9 August 2026, this Paper Citation Record lists 55 of 55 outbound references and 0 inbound Pith citation observations for arXiv:2608.05108.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links
A source-named dated measurement, never combined with another source.
Source: cited_works
Reference resolution
55 of 55 outbound references displayed
- verified exact0
- verified fuzzy26
- unresolved28
- parse uncertain0
- malformed identifier1
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation ce8157a8-3198-4805-9f11-09358257bf05 · outbound
This paper cites Ignore previous prompt: Attack techniques for language models,.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming Ignore previous prompt: Attack techniques for language models,
Reference 1
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T05:11:45.154237Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f2f22714-4efa-45ed-94b5-9bd9f4957670 · outbound
This paper cites Not what you’ve signed up for: Compromising real-world llm-integrated applications with indirect prompt injection,.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming Not what you’ve signed up for: Compromising real-world llm-integrated applications with indirect prompt injection,
Reference 2
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T05:11:56.781256Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation bd61774f-d9cd-4278-95d3-dcd980725294 · outbound
This paper cites Formalizing and benchmarking prompt injection attacks and defenses,.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming Formalizing and benchmarking prompt injection attacks and defenses,
Reference 3
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T05:11:56.674740Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 76d5a701-c412-4fe4-a7c4-3195dff7f224 · outbound
This paper cites Injecagent: Benchmarking indirect prompt injections in tool- integrated large language model agents,.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming Injecagent: Benchmarking indirect prompt injections in tool- integrated large language model agents,
Reference 4
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T05:11:56.473490Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation bde26fa6-ac1b-4460-aa32-edc540ebccec · outbound
This paper cites Agentdojo: A dynamic environment to evaluate prompt injection attacks and defenses for llm agents,.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming Agentdojo: A dynamic environment to evaluate prompt injection attacks and defenses for llm agents,
Reference 5
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T05:11:56.289540Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 14016feb-d5b0-4dd6-b8ab-4c41d96bc745 · outbound
This paper cites The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections
Reference 6
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T05:11:45.495675Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7c719ede-b99a-4713-8f57-90f3d7c72b39 · outbound
This paper cites Muse spark safety & preparedness report,.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming Muse spark safety & preparedness report,
Reference 7
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T05:11:56.149686Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 16083f83-3eea-4cce-ac70-1f620f990eab · outbound
This paper cites Claude opus 4.7 system card,.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming Claude opus 4.7 system card,
Reference 8
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T05:11:56.015812Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 23e69e23-13f4-44f8-a68b-54603f45fa10 · outbound
This paper cites Datasentinel: A game-theoretic detection of prompt injection attacks,.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming Datasentinel: A game-theoretic detection of prompt injection attacks,
Reference 9
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T05:11:55.853663Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation a610dc2b-5572-47b4-ba4c-9b8222a28ea6 · outbound
This paper cites PromptGuard Prompt Injection Guardrail,.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming PromptGuard Prompt Injection Guardrail,
Reference 10
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T05:11:55.674204Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation f1bf1c37-421f-42e8-a85b-5263240f4e08 · outbound
This paper cites AgentWatcher: A Rule-based Prompt Injection Monitor.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming AgentWatcher: A Rule-based Prompt Injection Monitor
Reference 11
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T05:11:45.854500Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation cb5317d7-a23e-4772-8e0c-cd71d6462d0b · outbound
This paper cites Meta secalign: A secure foundation llm against prompt injection attacks,.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming Meta secalign: A secure foundation llm against prompt injection attacks,
Reference 12
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T05:11:45.943166Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fccb7cd8-214d-4419-9e71-61df4f9a1633 · outbound
This paper cites Purple-teaming LLMs with Adversarial Defender Training.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming Purple-teaming LLMs with Adversarial Defender Training
Reference 13
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T05:11:45.995659Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 128eff0f-a175-4f43-85ee-a0e8d2807bf2 · outbound
This paper cites Black-box red-teaming of multi-agent systems via reinforcement learning,.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming Black-box red-teaming of multi-agent systems via reinforcement learning,
Reference 14
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T05:11:55.546133Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 1506dadd-4cfc-4288-87d3-46cd75cdeb52 · outbound
This paper cites Learning to Inject: Automated Prompt Injection via Reinforcement Learning.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming Learning to Inject: Automated Prompt Injection via Reinforcement Learning
Reference 15
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T05:11:46.111393Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6058760e-f676-4eeb-be9d-2d872b0e74d7 · outbound
This paper cites Rl is a hammer and llms are nails: A simple reinforcement learning recipe for strong prompt injection,.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming Rl is a hammer and llms are nails: A simple reinforcement learning recipe for strong prompt injection,
Reference 16
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T05:11:46.203274Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f8e5973a-ec6c-48b5-8515-b3a7e9413797 · outbound
This paper cites PISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming PISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses
Reference 17
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T05:11:46.310041Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 40477b0a-9b12-4a28-bfe1-36da9440ec23 · outbound
This paper cites Tree of attacks: Jailbreaking black-box llms automatically,.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming Tree of attacks: Jailbreaking black-box llms automatically,
Reference 18
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T05:11:46.382227Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7986393b-053b-411a-9513-0af5e38c9095 · outbound
This paper cites Jailbreaking black box large language models in twenty queries,.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming Jailbreaking black box large language models in twenty queries,
Reference 19
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T05:11:46.449184Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8b07b5e7-5bfc-4f94-a98d-05a9ccd7b76a · outbound
This paper cites Agentvigil: Automatic black-box red-teaming for indirect prompt injection against llm agents,.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming Agentvigil: Automatic black-box red-teaming for indirect prompt injection against llm agents,
Reference 20
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T05:11:55.370992Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 975147fa-4954-4812-8b14-8f12eb3df08d · outbound
This paper cites Piarena: A platform for prompt injection evaluation,.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming Piarena: A platform for prompt injection evaluation,
Reference 21
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T05:11:55.198269Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation d4dae2ee-2ff0-427c-83aa-68f923b3ab64 · outbound
This paper cites Gpt-red: Automated red teaming via self-play at scale.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming Gpt-red: Automated red teaming via self-play at scale
Reference 22
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T05:11:55.032827Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 6b1bbc84-dceb-4cd5-8669-4c88c9828352 · outbound
This paper cites How vulnerable are ai agents to indirect prompt injections? insights from a large-scale public competition,.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming How vulnerable are ai agents to indirect prompt injections? insights from a large-scale public competition,
Reference 23
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T05:11:46.711658Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f286f7ff-181a-40e7-8e00-de6f0b86b501 · outbound
This paper cites Muzzle: Adaptive agentic red-teaming of web agents against indirect prompt injection attacks,.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming Muzzle: Adaptive agentic red-teaming of web agents against indirect prompt injection attacks,
Reference 24
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T05:11:46.767256Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 66b2b30e-52df-4521-8173-9b09574fa6b6 · outbound
This paper cites Autodan- turbo: A lifelong agent for strategy self-exploration to jailbreak llms,.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming Autodan- turbo: A lifelong agent for strategy self-exploration to jailbreak llms,
Reference 25
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T05:11:54.785109Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 773492fa-d159-4a91-b778-4d6aac32070e · outbound
This paper cites DecodingTrust-Agent Platform (DTap): A Controllable and Interactive Red-Teaming Platform for AI Agents.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming DecodingTrust-Agent Platform (DTap): A Controllable and Interactive Red-Teaming Platform for AI Agents
Reference 26
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T05:11:46.996106Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ef34a227-74f2-469e-9719-296058853a8b · outbound
This paper cites ReAct: Synergizing Reasoning and Acting in Language Models.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming ReAct: Synergizing Reasoning and Acting in Language Models
Reference 27
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T05:11:47.055268Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 83da0063-c6d1-44d6-ad44-f293bc8c0929 · outbound
This paper cites Toolllm: Facilitating large language models to master 16000+ real-world apis,.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming Toolllm: Facilitating large language models to master 16000+ real-world apis,
Reference 28
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T05:11:54.496789Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation e32db511-3395-4a05-b2f4-daa3e63dbbf3 · outbound
This paper cites Autoharness: improving llm agents by automatically synthesizing a code harness,.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming Autoharness: improving llm agents by automatically synthesizing a code harness,
Reference 29
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T05:11:47.164645Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3e3a3567-d74d-46e1-965d-21c61d8ce21a · outbound
This paper cites Multi-agent Architecture Search via Agentic Supernet.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming Multi-agent Architecture Search via Agentic Supernet
Reference 30
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T05:11:47.247014Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 554b4a78-c0c9-49bb-8e1c-30dc5a1c2eaa · outbound
This paper cites TextGrad: Automatic "Differentiation" via Text.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming TextGrad: Automatic "Differentiation" via Text
Reference 31
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T05:11:47.342591Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3c0af994-60f6-4303-96f5-c5a3d88969e6 · outbound
This paper cites Test-time training with self-supervision for generalization under distribution shifts,.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming Test-time training with self-supervision for generalization under distribution shifts,
Reference 32
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T05:11:54.272634Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 4761427b-17af-4cfc-94f1-f0fe0af33f58 · outbound
This paper cites Gemini CLI: An open-source AI agent for the terminal,.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming Gemini CLI: An open-source AI agent for the terminal,
Reference 33
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T05:11:54.073223Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 5a1b9b39-aa08-4a74-b822-af031cc6d786 · outbound
This paper cites Codex CLI: A lightweight coding agent that runs in your terminal,.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming Codex CLI: A lightweight coding agent that runs in your terminal,
Reference 34
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T05:11:53.825124Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation b8b85a14-c728-4f94-8f93-c37e7e3f8b8d · outbound
This paper cites Claw code: A clean-room open-source coding-agent CLI,.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming Claw code: A clean-room open-source coding-agent CLI,
Reference 35
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T05:11:53.561952Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation c49965f8-9100-48da-8537-c1ebcda2ae54 · outbound
This paper cites Hermes agent: An open-source self-hosted autonomous AI agent,.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming Hermes agent: An open-source self-hosted autonomous AI agent,
Reference 36
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T05:11:53.262640Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 72716773-1290-4acc-85d2-783456d67671 · outbound
This paper cites Claude code: An agentic coding tool for the terminal,.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming Claude code: An agentic coding tool for the terminal,
Reference 37
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T05:11:53.011248Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 03c25b03-505b-4056-9caa-f7d8060cf3a2 · outbound
This paper cites Attention tracker: Detecting prompt injection attacks in llms,.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming Attention tracker: Detecting prompt injection attacks in llms,
Reference 38
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T05:11:52.823611Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 6bf302bb-3a4c-4b99-9e42-3f29ecb6f5dd · outbound
This paper cites Piguard: Prompt injection guardrail via mitigating overdefense for free,.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming Piguard: Prompt injection guardrail via mitigating overdefense for free,
Reference 39
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T05:11:52.534030Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 4c31e5f5-4e0d-4b42-9b48-68ca1a65e058 · outbound
This paper cites Pishield: Detecting prompt injection attacks via intrinsic llm features,.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming Pishield: Detecting prompt injection attacks via intrinsic llm features,
Reference 40
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T05:11:47.884895Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b87c2d68-6b1a-4788-97cb-a45d674b1b06 · outbound
This paper cites Pisanitizer: Preventing prompt injection to long-context llms via prompt sanitization,.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming Pisanitizer: Preventing prompt injection to long-context llms via prompt sanitization,
Reference 41
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T05:11:47.889944Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 407bed97-eabb-4702-8561-0b84d15625bf · outbound
This paper cites PromptArmor: Simple yet Effective Prompt Injection Defenses.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming PromptArmor: Simple yet Effective Prompt Injection Defenses
Reference 42
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T05:11:47.970675Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 333ca45e-6c47-4e83-9f80-76610928175c · outbound
This paper cites Defending against prompt injection with datafilter,.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming Defending against prompt injection with datafilter,
Reference 43
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T05:11:48.140727Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 059b8f4f-e9f5-4311-a80e-d78b91967332 · outbound
This paper cites Defeating Prompt Injections by Design.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming Defeating Prompt Injections by Design
Reference 44
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T05:11:48.276646Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 82359524-7b03-44e3-a8b2-982d4129ad90 · outbound
This paper cites Drift: Dynamic rule-based defense with injection isolation for securing llm agents,.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming Drift: Dynamic rule-based defense with injection isolation for securing llm agents,
Reference 45
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T05:11:52.260009Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation d8392da2-dc0a-404f-91c0-488d8251085d · outbound
This paper cites AgentDyn: Are Your Agent Security Defenses Deployable in Real-World Dynamic Environments?.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming AgentDyn: Are Your Agent Security Defenses Deployable in Real-World Dynamic Environments?
Reference 46
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T05:11:48.601504Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c23152a6-c5e5-4cd2-a546-fbde8379b1b4 · outbound
This paper cites Claude opus 4.8 system card,.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming Claude opus 4.8 system card,
Reference 47
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T05:11:51.990541Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation d09fb8ad-d715-4abd-8272-6f2a4d75c615 · outbound
This paper cites Secalign: Defend- ing against prompt injection with preference optimization,.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming Secalign: Defend- ing against prompt injection with preference optimization,
Reference 48
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T05:11:51.702584Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 9f07afa9-9677-4cdc-8795-3b858e9f8935 · outbound
This paper cites The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions
Reference 49
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T05:11:48.996878Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c7126831-551e-4344-84b8-ffab5e6054f3 · outbound
This paper cites an unresolved cited work.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming Unresolved cited work
Reference 50
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T05:11:51.514757Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation f5074bf4-fd08-4704-b766-4b57a2c2cdc8 · outbound
This paper cites an unresolved cited work.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming Unresolved cited work
Reference 51
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T05:11:51.296756Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation c1fea9e2-c54c-47e1-b6a8-1f3ee21011a3 · outbound
This paper cites an unresolved cited work.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming Unresolved cited work
Reference 52
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T05:11:51.021691Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation b27962e6-48cf-4f7a-b695-dcc41b949dc2 · outbound
This paper cites an unresolved cited work.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming Unresolved cited work
Reference 53
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T05:11:50.833130Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation dc2a7192-903f-4f9e-bae5-1e721339cad3 · outbound
This paper cites ## In-context examples.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming ## In-context examples
Reference 54
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T05:11:50.559662Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation a1f25a28-a12e-4227-91e7-d3686e6a9dcf · outbound
This paper cites ## When this strategy is expected to fail.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming ## When this strategy is expected to fail
Reference 55
- Resolution
- malformed identifier
- raw_fallback, observed 2026-08-06T05:11:50.294110Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Pith citing papers
No inbound Pith citation observations are available.