Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-07T00:12:27.078558Z
Paper Citation Record · LEDGER
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance
As of 7 August 2026, this Paper Citation Record lists 55 of 55 outbound references and 0 inbound Pith citation observations for arXiv:2608.01558.
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 2026-08-07T06:34:17.273281+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 exact6
- verified fuzzy10
- unresolved39
- parse uncertain0
- malformed identifier0
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation d90b0aef-fc35-4176-9847-d71e7c2998a8 · outbound
This paper cites 2024.System architecture for the 5G System (TS 23.501).
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance 2024.System architecture for the 5G System (TS 23.501)
Reference 1
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T00:13:00.575025Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 508f4b3a-d805-4f3d-8234-47afce6c2e12 · outbound
This paper cites Security Threat Modeling for Emerging AI-Agent Protocols: A Comparative Analysis of MCP, A2A, Agora, and ANP.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance Security Threat Modeling for Emerging AI-Agent Protocols: A Comparative Analysis of MCP, A2A, Agora, and ANP
Reference 2
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T00:12:22.935267Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b7dfa417-2d66-441a-9b2b-2fb93ac7d73e · outbound
This paper cites an unresolved cited work.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance Unresolved cited work
Reference 3
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T00:12:23.018725Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7655f297-4550-4aee-b806-2a18b97ac2eb · outbound
This paper cites an unresolved cited work.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance Unresolved cited work
Reference 4
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T00:12:23.119614Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c3facac2-0e00-4c0c-aed9-bbd8c38eb557 · outbound
This paper cites an unresolved cited work.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance Unresolved cited work
Reference 5
- Resolution
- verified exact
- raw_fallback, observed 2026-08-07T00:12:58.790971Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation f332cb43-44ed-47b3-bb15-2d598316e784 · outbound
This paper cites AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases
Reference 6
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T00:12:23.283898Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 345b9450-26d8-49f5-97a3-22b13a5d5372 · outbound
This paper cites 2012.Computer Security Incident Handling Guide (NIST SP 800-61 Rev.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance 2012.Computer Security Incident Handling Guide (NIST SP 800-61 Rev
Reference 7
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T00:13:00.545974Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 4982389e-3cb7-4eef-841b-8e46e62152cf · outbound
This paper cites 2025.Securing AI Agents with Cisco’s Open-Source A2A Scanner.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance 2025.Securing AI Agents with Cisco’s Open-Source A2A Scanner
Reference 8
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T00:13:00.531905Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 12a6028b-46e2-497f-9099-3e687c51ea92 · outbound
This paper cites an unresolved cited work.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance Unresolved cited work
Reference 9
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T00:13:00.518070Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation a7a7e11a-186f-4033-a1fb-0de4a6ce2a25 · outbound
This paper cites Here Comes The AI Worm: Unleashing Zero-click Worms that Target GenAI-Powered Applications.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance Here Comes The AI Worm: Unleashing Zero-click Worms that Target GenAI-Powered Applications
Reference 10
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T00:12:23.578617Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b560053b-4adf-47e6-85ef-147adec35fd9 · outbound
This paper cites Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges
Reference 11
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T00:12:23.625640Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 752afc91-068b-4e94-8e2c-55e86530c623 · outbound
This paper cites Defeating Prompt Injections by Design.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance Defeating Prompt Injections by Design
Reference 12
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T00:12:23.711741Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0d707773-6112-4200-91d1-82a20796ddbe · outbound
This paper cites AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
Reference 13
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T00:12:23.784463Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0f5ac053-9f9d-4e43-b4f2-62f43889da4c · outbound
This paper cites A survey of agent interoperability protocols: Model Context Protocol (MCP), Agent Communication Protocol (ACP), Agent-to-Agent Protocol (A2A), and Agent Network Protocol (ANP).
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance A survey of agent interoperability protocols: Model Context Protocol (MCP), Agent Communication Protocol (ACP), Agent-to-Agent Protocol (A2A), and Agent Network Protocol (ANP)
Reference 14
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T00:12:23.867036Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ed5b273b-06c8-40a4-81ea-7e1a09c5f7d9 · outbound
This paper cites 2018.MiFID II Articles 17 and 21; RTS 6 Algorithmic Trading.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance 2018.MiFID II Articles 17 and 21; RTS 6 Algorithmic Trading
Reference 15
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T00:13:00.503952Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 76b2a1c9-1e9e-4e20-9bc0-1a529b3408ad · outbound
This paper cites an unresolved cited work.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance Unresolved cited work
Reference 16
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T00:12:24.077540Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a97c45a7-0929-471c-ab3a-90dd132c3903 · outbound
This paper cites 2025.Safeguarding AI Agents: An In-Depth Look at A2A Protocol Risks.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance 2025.Safeguarding AI Agents: An In-Depth Look at A2A Protocol Risks
Reference 17
- Resolution
- verified exact
- raw_fallback, observed 2026-08-07T00:12:58.569959Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation b4d4b2f8-ca56-4a56-b4a8-c9e594d47e4d · outbound
This paper cites an unresolved cited work.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance Unresolved cited work
Reference 18
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T00:13:00.489856Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 3fb1543d-b560-4271-9859-6410d51c2893 · outbound
This paper cites 2023.HL7 FHIR Release 5: Workflow Module.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance 2023.HL7 FHIR Release 5: Workflow Module
Reference 19
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T00:13:00.474737Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 096cf875-d7a9-4935-94c6-3b4e673fa876 · outbound
This paper cites Don't Make Models Guess Security and Safety: Symbolic Guardrails for Domain-Specific AI Agents.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance Don't Make Models Guess Security and Safety: Symbolic Guardrails for Domain-Specific AI Agents
Reference 20
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T00:12:24.400080Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 52e314d6-b13d-4526-b304-b05bfdc6b52e · outbound
This paper cites RepetitionCurse: Measuring and Understanding Router Imbalance in Mixture-of-Experts LLMs under DoS Stress.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance RepetitionCurse: Measuring and Understanding Router Imbalance in Mixture-of-Experts LLMs under DoS Stress
Reference 21
- Resolution
- verified exact
- local_arxiv, observed 2026-08-07T00:12:58.362037Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 456f57e7-6c97-4e49-ae3e-09d5ecce964c · outbound
This paper cites an unresolved cited work.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance Unresolved cited work
Reference 22
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T00:13:00.459263Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation e610b514-8243-471d-b14b-65abcb25fd59 · outbound
This paper cites an unresolved cited work.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance Unresolved cited work
Reference 23
- Resolution
- verified exact
- doi, observed 2026-08-07T00:12:42.649877Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 663c4715-075b-4a8b-933e-70c67598f1ee · outbound
This paper cites 2025.Potential Attack Surfaces in Agent2Agent (A2A) Protocol.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance 2025.Potential Attack Surfaces in Agent2Agent (A2A) Protocol
Reference 24
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T00:13:00.442944Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 71f63925-21cb-4534-a09f-99c0f9fa8664 · outbound
This paper cites an unresolved cited work.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance Unresolved cited work
Reference 25
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T00:12:24.716939Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 78243060-5fa4-4890-ae64-9c6f4248e067 · outbound
This paper cites an unresolved cited work.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance Unresolved cited work
Reference 26
- Resolution
- verified exact
- doi, observed 2026-08-07T00:12:42.470683Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation eb452181-ee18-4f62-b1ca-0d1bae3a2c5b · outbound
This paper cites 2025.ACP Joins Forces with A2A Under the Linux Foundation’s LF AI & Data.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance 2025.ACP Joins Forces with A2A Under the Linux Foundation’s LF AI & Data
Reference 27
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T00:13:00.427440Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 6fde1e6d-e018-42c1-87af-c49f61f02043 · outbound
This paper cites Life-Cycle Routing Vulnerabilities of LLM Router.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance Life-Cycle Routing Vulnerabilities of LLM Router
Reference 28
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T00:12:24.911258Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 77a0b4f7-0765-4890-b4a2-52ac4e864081 · outbound
This paper cites an unresolved cited work.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance Unresolved cited work
Reference 29
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T00:13:00.411614Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 87e5d589-ed43-460a-8cb5-72f0bc6e0714 · outbound
This paper cites an unresolved cited work.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance Unresolved cited work
Reference 30
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T00:13:00.392032Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation cf032acd-a091-4d9c-909e-04c7a881af85 · outbound
This paper cites an unresolved cited work.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance Unresolved cited work
Reference 31
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T00:12:25.092502Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 60075151-2517-4ac8-ac33-6151af36fca9 · outbound
This paper cites Security Considerations for Multi-agent Systems.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance Security Considerations for Multi-agent Systems
Reference 32
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T00:12:25.164426Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7ed7363c-916d-4dcb-9bbd-887ab9a97125 · outbound
This paper cites an unresolved cited work.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance Unresolved cited work
Reference 33
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T00:13:00.371119Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 544baad3-4d8c-42f8-a7f7-8094c98cfb95 · outbound
This paper cites an unresolved cited work.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance Unresolved cited work
Reference 34
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T00:13:00.347754Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 6c6d1120-29b5-4128-9578-f9c013ce9061 · outbound
This paper cites an unresolved cited work.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance Unresolved cited work
Reference 35
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T00:13:00.331578Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 3b43a8ba-78a0-4810-96b4-396a523c4364 · outbound
This paper cites an unresolved cited work.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance Unresolved cited work
Reference 36
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T00:13:00.307043Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 5c4db43f-afef-4d0f-bc0e-1af3fed63b7b · outbound
This paper cites Under the Hood of SKILL.md: Semantic Supply-chain Attacks on AI Agent Skill Registry.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance Under the Hood of SKILL.md: Semantic Supply-chain Attacks on AI Agent Skill Registry
Reference 37
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T00:12:25.516024Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 75121b02-8aed-4888-91cd-87613c0d45a6 · outbound
This paper cites 2026.A2A Protocol Security: Authenticating Agent-to-Agent Communi- cation.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance 2026.A2A Protocol Security: Authenticating Agent-to-Agent Communi- cation
Reference 38
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T00:13:00.272211Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 446a917b-4392-4785-8152-6b8b809c6b60 · outbound
This paper cites an unresolved cited work.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance Unresolved cited work
Reference 39
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T00:13:00.036365Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 6d5755eb-7184-4249-bc1f-95add8c6fd6c · outbound
This paper cites Prompt Injection Attack to Tool Selection in LLM Agents.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance Prompt Injection Attack to Tool Selection in LLM Agents
Reference 40
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T00:12:25.831378Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 32663088-c234-4639-84e0-42d246b24447 · outbound
This paper cites Progent: Securing AI Agents with Privilege Control.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance Progent: Securing AI Agents with Privilege Control
Reference 41
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T00:12:25.895446Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ed50bcb4-1f05-445a-b2ce-2b59540e69d4 · outbound
This paper cites Route to Rome Attack: Directing LLM Routers to Expensive Models via Adversarial Suffix Optimization.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance Route to Rome Attack: Directing LLM Routers to Expensive Models via Adversarial Suffix Optimization
Reference 42
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T00:12:26.015766Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 57a63382-f3dc-43ee-8317-8b52ef0cdab6 · outbound
This paper cites 2025.Linux Foundation Announces the Forma- tion of the Agentic AI Foundation (AAIF).
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance 2025.Linux Foundation Announces the Forma- tion of the Agentic AI Foundation (AAIF)
Reference 43
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T00:12:59.835938Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 8679f679-8ad9-410a-8543-f962ff3dd360 · outbound
This paper cites 2025.Linux Foundation Launches the Agent2Agent Protocol Project to Enable Secure, Intelligent Communication Between AI Agents.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance 2025.Linux Foundation Launches the Agent2Agent Protocol Project to Enable Secure, Intelligent Communication Between AI Agents
Reference 44
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T00:12:59.269986Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 21ad1643-490a-4954-a7ff-b87eb2d7bfad · outbound
This paper cites an unresolved cited work.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance Unresolved cited work
Reference 45
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T00:12:59.543610Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 84c6b314-84ef-488c-8ddd-afc663ba51d0 · outbound
This paper cites AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents
Reference 46
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T00:12:26.491944Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 30284983-2ca0-436a-9563-ea2437dc1589 · outbound
This paper cites an unresolved cited work.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance Unresolved cited work
Reference 47
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T00:12:59.017385Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 36cfab86-09f9-4d41-beae-26d34d1865e7 · outbound
This paper cites an unresolved cited work.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance Unresolved cited work
Reference 48
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T00:12:26.677481Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1867f1c6-7164-4a3b-ad41-b75d7b65c53e · outbound
This paper cites ProbGuard: Proactive Runtime Monitoring for LLM Agent Safety via Probabilistic Prediction.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance ProbGuard: Proactive Runtime Monitoring for LLM Agent Safety via Probabilistic Prediction
Reference 49
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T00:12:26.587196Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b46de631-1721-4aa0-8f88-30252ed74380 · outbound
This paper cites Stealing User Prompts from Mixture of Experts.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance Stealing User Prompts from Mixture of Experts
Reference 50
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T00:12:26.839942Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6b32b77d-b644-4426-be8a-c43df23e9368 · outbound
This paper cites RouteHijack: Routing-Aware Attack on Mixture-of-Experts LLMs.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance RouteHijack: Routing-Aware Attack on Mixture-of-Experts LLMs
Reference 51
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T00:12:26.741411Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6baedb92-ac0c-4dd5-a071-338cecee1a3b · outbound
This paper cites an unresolved cited work.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance Unresolved cited work
Reference 52
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T00:12:27.004844Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 364c5f77-8357-4899-aab5-bf48bd693a52 · outbound
This paper cites an unresolved cited work.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance Unresolved cited work
Reference 53
- Resolution
- verified exact
- raw_fallback, observed 2026-08-07T00:12:42.992528Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation b762fbc8-2f22-4c04-afaf-36ca9dbed0c2 · outbound
This paper cites PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models
Reference 55
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T00:12:27.078558Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 08950bca-1daa-4dde-8a86-4f1e282ff083 · outbound
This paper cites Rerouting LLM Routers.
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance Rerouting LLM Routers
Reference 2025
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T00:12:25.735180Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Pith citing papers
No inbound Pith citation observations are available.