Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario | Paper Citation Record

Observation 9b442563-4922-47c9-85cc-b4c8858ed49e · outbound

This paper cites Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-12T00:27:39.724833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 309e5243-f2cf-4c56-9691-9e60d0382dfd · outbound

This paper cites Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples,.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-12T00:27:39.755114Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 956ce005-9583-4196-a8d1-79c6a4d7b282 · outbound

This paper cites BadAgent: Inserting and Activating Backdoor Attacks in LLM Agents,.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario BadAgent: Inserting and Activating Backdoor Attacks in LLM Agents,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-12T00:27:39.796017Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2e9abdf-113b-4826-89be-c03f17de142f · outbound

This paper cites AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases,.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:27:48.674850Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 9dc28dc3-f513-470d-8c30-27ff1fdfcfe4 · outbound

This paper cites MemoryGraft: Persistent Compromise of LLM Agents via Poisoned Experience Retrieval,.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario MemoryGraft: Persistent Compromise of LLM Agents via Poisoned Experience Retrieval,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-12T00:27:39.885649Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02791b60-b0b8-4fb7-ab4d-e39b756280c3 · outbound

This paper cites MemMorph: Tool Hijacking in LLM Agents via Memory Poisoning.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario MemMorph: Tool Hijacking in LLM Agents via Memory Poisoning

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-12T00:27:39.928535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41fdd77f-ba8c-4212-8d29-5b27157f952e · outbound

This paper cites Your LLM Agent Can Leak Your Data: Data Exfiltration via Backdoored Tool Use,.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario Your LLM Agent Can Leak Your Data: Data Exfiltration via Backdoored Tool Use,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:27:48.524756Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 863a6853-327a-4029-befe-468aefb5cf7e · outbound

This paper cites TrojanStego: Your Language Model Can Secretly Be A Steganographic Privacy Leaking Agent,.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario TrojanStego: Your Language Model Can Secretly Be A Steganographic Privacy Leaking Agent,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-12T00:27:40.044762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8d20b37-935f-480c-aac7-04448fb7bdf1 · outbound

This paper cites BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models,.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:27:48.354775Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation d0603caf-fb05-4bc1-969b-7889702e85ce · outbound

This paper cites Not What You’ve Signed Up For: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection,.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario Not What You’ve Signed Up For: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-12T00:27:40.119007Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8f36127-fa5a-4672-aba4-460fd160a830 · outbound

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

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-12T00:27:40.164821Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90e09d21-ab08-4f6f-bdc5-07fb1cc706b1 · outbound

This paper cites The UNSTOPPABLE Computer Virus is HERE...,.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario The UNSTOPPABLE Computer Virus is HERE...,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:27:48.223407Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 28cf8109-f145-4469-93e5-b9c6cc521c6f · outbound

This paper cites Inhibitor Chip,.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario Inhibitor Chip,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:27:48.135312Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 5545133a-5795-413f-89f0-c74741f32cce · outbound

This paper cites Here Comes The AI Worm: Unleashing Zero-click Worms that Target GenAI-Powered Applications.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario Here Comes The AI Worm: Unleashing Zero-click Worms that Target GenAI-Powered Applications

Reference 14

Resolution: malformed identifier; no resolver link, observed 2026-08-12T00:27:40.294752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28840d74-d48d-450b-82b2-9c346948f179 · outbound

This paper cites AgentWorm: Self-Propagating Attacks Across LLM Agent Ecosystems.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario AgentWorm: Self-Propagating Attacks Across LLM Agent Ecosystems

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-12T00:27:40.330332Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4eaffcdb-2844-426b-8fa3-1d5e56c9b88c · outbound

This paper cites Agent Harness Plugins,.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario Agent Harness Plugins,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:27:48.037153Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 56dbd000-8080-4d1a-9661-08e9fd42b32b · outbound

This paper cites Sandboxing,.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario Sandboxing,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:27:47.895176Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation f08083ad-512a-4fea-849c-1f0fcac7ae78 · outbound

This paper cites AI Agents Enable Adaptive Computer Worms.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario AI Agents Enable Adaptive Computer Worms

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-12T00:27:40.475237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c56bdc4-213e-4f59-9a2b-b4bc8351a96b · outbound

This paper cites an unresolved cited work.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario Unresolved cited work

Reference 19

Resolution: malformed identifier; raw_fallback, observed 2026-08-12T00:27:47.744850Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 7e82f5d8-4a84-4efe-bcbf-ebe065d46d41 · outbound

This paper cites "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-12T00:27:40.575004Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2003454a-7efe-4ef3-8e63-347f64e90bb7 · outbound

This paper cites The Promptware Kill Chain: How Prompt Injections Gradually Evolved Into a Multistep Malware Delivery Mechanism,.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario The Promptware Kill Chain: How Prompt Injections Gradually Evolved Into a Multistep Malware Delivery Mechanism,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-12T00:27:40.597003Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19e34c6d-af88-4013-ac20-e54116b07705 · outbound

This paper cites The Trigger in the Haystack: Extracting and Reconstructing LLM Backdoor Triggers,.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario The Trigger in the Haystack: Extracting and Reconstructing LLM Backdoor Triggers,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-12T00:27:40.644753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d6a537f-752f-4b1f-820e-cd9af7f1dfb4 · outbound

This paper cites an unresolved cited work.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario Unresolved cited work

Reference 23

Resolution: unresolved; raw_fallback, observed 2026-08-12T00:27:47.582954Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 4d6b4293-8dd0-4f9f-9f70-1d5c1573410b · outbound

This paper cites Data Scientists Targeted by Malicious Hugging Face ML Models with Silent Backdoor,.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario Data Scientists Targeted by Malicious Hugging Face ML Models with Silent Backdoor,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:27:47.433652Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 82a30afb-a12e-442f-ae1d-9ad47e106730 · outbound

This paper cites Malicious ML Models Discovered on Hugging Face Platform,.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario Malicious ML Models Discovered on Hugging Face Platform,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:27:47.287910Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 36629ec0-20e0-47c0-9741-962c43c5f3cd · outbound

This paper cites Vassilev, A.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario Vassilev, A

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-12T00:27:40.816629Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61973191-b00b-4015-97bc-139ac8f0acb1 · outbound

This paper cites OpenAI and Hugging Face Partner to Address Security Incident During Model Evaluation,.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario OpenAI and Hugging Face Partner to Address Security Incident During Model Evaluation,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:27:47.124754Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation e055b162-a25d-45f2-a4b9-830aa4120bc4 · outbound

This paper cites Third-Party Cyber Evaluations Involving OpenAI Models,.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario Third-Party Cyber Evaluations Involving OpenAI Models,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:27:46.960857Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation c788fb0b-dc77-430c-80c3-009f7d47f6b1 · outbound

This paper cites Security Incident Disclosure—July 2026,.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario Security Incident Disclosure—July 2026,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:27:46.836194Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation f4312c69-80d4-4956-9d95-51246b8ea4b5 · outbound

This paper cites Anatomy of a Frontier Lab Agent Intrusion: A Technical Timeline of the July 2026 Incident,.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario Anatomy of a Frontier Lab Agent Intrusion: A Technical Timeline of the July 2026 Incident,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:27:46.777605Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation aa867b46-3ae5-4694-a18a-155bf11a5e6a · outbound

This paper cites Investigating Three Real-World Incidents in Our Cybersecurity Evaluations,.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario Investigating Three Real-World Incidents in Our Cybersecurity Evaluations,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:27:46.694829Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 9f1afd4d-e07f-4588-bac1-3404a195b73a · outbound

This paper cites CVE-2025-32711 Detail,.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario CVE-2025-32711 Detail,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:27:46.558954Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 9388d3cc-4e1f-4e0c-bcda-c6099742e650 · outbound

This paper cites CVE-2025-32711: AI Command Injection in M365 Copilot,.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario CVE-2025-32711: AI Command Injection in M365 Copilot,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:27:46.423653Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation db074430-105e-4bec-b1c9-00adb4c43d7f · outbound

This paper cites Microsoft 365 Copilot: New Zero-Click AI Vulnerability Allows Corporate Data Theft,.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario Microsoft 365 Copilot: New Zero-Click AI Vulnerability Allows Corporate Data Theft,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:27:46.364752Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 63282f5e-41cd-41f0-be87-99ca0a7db54c · outbound

This paper cites ShadowLeak: A Zero-Click, Service-Side Attack Exfiltrating Sensitive Data Using ChatGPT’s Deep Research Agent,.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario ShadowLeak: A Zero-Click, Service-Side Attack Exfiltrating Sensitive Data Using ChatGPT’s Deep Research Agent,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:27:46.194755Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 275b5edd-67ca-48af-8abb-07aa01d72b09 · outbound

This paper cites MCP Security Notification: Tool Poisoning Attacks,.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario MCP Security Notification: Tool Poisoning Attacks,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:27:46.104833Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 2c918cec-6937-4f0f-9753-7749515e1915 · outbound

This paper cites Memory Injection Attacks on LLM Agents via Query-Only Interaction,.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario Memory Injection Attacks on LLM Agents via Query-Only Interaction,

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-12T00:27:41.244758Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d260514-6c10-4e62-a59f-3dc253b05baf · outbound

This paper cites Hidden in Memory: Sleeper Memory Poisoning in LLM Agents.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario Hidden in Memory: Sleeper Memory Poisoning in LLM Agents

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-12T00:27:41.285934Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ece7a236-3d8c-492c-93d0-0049317b5277 · outbound

This paper cites From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agents.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agents

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-12T00:27:41.324755Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72c09d27-fabc-483a-99d9-d59ee8df0cdb · outbound

This paper cites Malicious Script Injected into Amazon Q Developer for Visual Studio Code Extension,.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario Malicious Script Injected into Amazon Q Developer for Visual Studio Code Extension,

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:27:45.964752Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 206df232-0946-48f4-9c81-a7f626d399b0 · outbound

This paper cites The Shai-Hulud 2.0 npm Worm: Analysis, and What You Need to Know,.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario The Shai-Hulud 2.0 npm Worm: Analysis, and What You Need to Know,

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:27:45.774752Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 16557417-335a-49e2-91ed-a3b236408ba3 · outbound

This paper cites Mini Shai-Hulud Targets AI Coding Agents: What Developers Need to Know,.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario Mini Shai-Hulud Targets AI Coding Agents: What Developers Need to Know,

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:27:45.718381Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 8d95a65c-3bfe-4bd2-80a0-d4b02a192e85 · outbound

This paper cites Malicious Versions of Nx and Some Supporting Plugins Were Published,.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario Malicious Versions of Nx and Some Supporting Plugins Were Published,

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:27:45.658413Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation be436981-7b99-4150-9824-21f084263a47 · outbound

This paper cites S1ngularity—What Happened, How We Responded, What We Learned,.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario S1ngularity—What Happened, How We Responded, What We Learned,

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:27:45.611636Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 3118362f-c399-4125-9f87-1379f6c537d1 · outbound

This paper cites s1ngularity’s Aftermath: AI, TTPs, and Impact in the Nx Supply Chain Attack,.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario s1ngularity’s Aftermath: AI, TTPs, and Impact in the Nx Supply Chain Attack,

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:27:45.454870Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 6965fcf9-ccdd-4b94-8957-ee503a9a4319 · outbound

This paper cites The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-12T00:27:41.664753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45473cc3-8b2c-48a0-aade-579c56545a91 · outbound

This paper cites Defeating Prompt Injections by Design.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario Defeating Prompt Injections by Design

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-12T00:27:41.714833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aafcb72c-b0e1-4e7e-8b3c-d1338d5b885a · outbound

This paper cites Progent: Securing AI Agents with Privilege Control.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario Progent: Securing AI Agents with Privilege Control

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-12T00:27:41.761861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4b0cd2a-7794-4d12-9b9e-0bca5f34dd36 · outbound

This paper cites SimpleProbesCanCatchSleeperAgents,.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario SimpleProbesCanCatchSleeperAgents,

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:27:45.293751Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation d6d80a9c-2279-4710-a40c-5e22bea4761c · outbound

This paper cites Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-12T00:27:41.854957Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2bba3fb2-0c36-4420-8b6b-f06ebde0f077 · outbound

This paper cites Agentic Misalignment: How LLMs Could Be Insider Threats,.

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario Agentic Misalignment: How LLMs Could Be Insider Threats,

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:27:45.179187Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers