Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-05-14T22:16:56.848520Z
Paper Citation Record · LEDGER
Evaluating Privilege Usage of Agents with Real-World Tools
As of 6 August 2026, this Paper Citation Record lists 23 of 23 outbound references and 4 inbound Pith citation observations for arXiv:2603.28166.
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 2026-08-06T06:34:29.942622+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-05-19T23:26:15.658106Z
A source-named dated measurement, never combined with another source.
Source: pith, observed 2026-05-19T23:27:52.444391Z
Reference resolution
23 of 23 outbound references displayed
- verified exact13
- verified fuzzy0
- unresolved7
- parse uncertain0
- malformed identifier2
- metadata mismatch1
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 0f62c6ea-9b8c-4a93-ba25-dd50aae33835 · outbound
This paper cites an unresolved cited work.
Evaluating Privilege Usage of Agents with Real-World Tools Unresolved cited work
Reference 1
- Resolution
- unresolved
- raw_fallback, observed 2026-05-14T22:18:05.872178Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 79870d60-48e9-41de-9775-71fde54eecfa · outbound
This paper cites Proceedings of the 2025.
Evaluating Privilege Usage of Agents with Real-World Tools Proceedings of the 2025
Reference 2
- Resolution
- verified exact
- doi, observed 2026-05-14T22:18:03.393538Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation c43bd667-9f0e-4533-acc6-ee58228d41cd · outbound
This paper cites an unresolved cited work.
Evaluating Privilege Usage of Agents with Real-World Tools Unresolved cited work
Reference 3
- Resolution
- unresolved
- raw_fallback, observed 2026-05-14T22:18:05.867593Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 098409ae-934e-4a18-802a-7d9d27c447c6 · outbound
This paper cites an unresolved cited work.
Evaluating Privilege Usage of Agents with Real-World Tools Unresolved cited work
Reference 4
- Resolution
- verified exact
- doi, observed 2026-05-14T22:18:03.410366Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 40ddf811-1ace-4073-827f-239940e1f6df · outbound
This paper cites Defeating Prompt Injections by Design.
Evaluating Privilege Usage of Agents with Real-World Tools Defeating Prompt Injections by Design
Reference 5
- Resolution
- verified exact
- local_arxiv, observed 2026-05-14T22:18:04.353353Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 6dfb4c78-c581-4820-8055-b2357936c95f · outbound
This paper cites an unresolved cited work.
Evaluating Privilege Usage of Agents with Real-World Tools Unresolved cited work
Reference 6
- Resolution
- unresolved
- raw_fallback, observed 2026-05-14T22:18:05.889426Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 5bde3dfb-c2a5-4f70-8126-66898e66105a · outbound
This paper cites an unresolved cited work.
Evaluating Privilege Usage of Agents with Real-World Tools Unresolved cited work
Reference 7
- Resolution
- unresolved
- raw_fallback, observed 2026-05-14T22:18:05.863104Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 1aab66c6-34ae-4d9e-bdaf-350397be20b1 · outbound
This paper cites RAS-Eval: A Comprehensive Benchmark for Security Evaluation of LLM Agents in Real-World Environments.
Evaluating Privilege Usage of Agents with Real-World Tools RAS-Eval: A Comprehensive Benchmark for Security Evaluation of LLM Agents in Real-World Environments
Reference 8
- Resolution
- verified exact
- arxiv_id, observed 2026-05-14T22:18:04.361136Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 8c670657-3759-4614-823b-82f44229b76e · outbound
This paper cites InProceedings of the 16th ACM Workshop on Artificial Intelligence and Security (AISec @ CCS 2023).
Evaluating Privilege Usage of Agents with Real-World Tools InProceedings of the 16th ACM Workshop on Artificial Intelligence and Security (AISec @ CCS 2023)
Reference 9
- Resolution
- verified exact
- arxiv_id, observed 2026-05-14T22:18:03.355125Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 236473ac-8897-448b-80f9-c27afc936abc · outbound
This paper cites Don’t Forget the Teachers.
Evaluating Privilege Usage of Agents with Real-World Tools Don’t Forget the Teachers
Reference 10
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-14T22:18:03.371857Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 36cf52ab-80bb-445c-ad7c-815346045032 · outbound
This paper cites Delegated authorization for agents constrained to semantic task-to-scope matching.
Evaluating Privilege Usage of Agents with Real-World Tools Delegated authorization for agents constrained to semantic task-to-scope matching
Reference 11
- Resolution
- verified exact
- arxiv_id, observed 2026-05-14T22:18:04.373916Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 9c3e0028-6341-4b93-88fa-c553aaa26fd4 · outbound
This paper cites Agent-RewardBench: Towards a unified benchmark for reward modeling across perception, planning, and safety in real- world multimodal agents.
Evaluating Privilege Usage of Agents with Real-World Tools Agent-RewardBench: Towards a unified benchmark for reward modeling across perception, planning, and safety in real- world multimodal agents
Reference 12
- Resolution
- malformed identifier
- doi_truncated, observed 2026-05-14T22:18:03.378474Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 5d857eb3-6c95-4746-9d07-b33b0d7086ad · outbound
This paper cites DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models.
Evaluating Privilege Usage of Agents with Real-World Tools DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
Reference 13
- Resolution
- verified exact
- local_arxiv, observed 2026-05-14T22:18:04.333729Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 1fdd51fd-7a93-4856-b9af-770eeb0dae9c · outbound
This paper cites Prompt Injection attack against LLM-integrated Applications.
Evaluating Privilege Usage of Agents with Real-World Tools Prompt Injection attack against LLM-integrated Applications
Reference 14
- Resolution
- verified exact
- local_arxiv, observed 2026-05-14T22:18:04.367445Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 84967782-3115-4475-a7d3-13bd054e62d1 · outbound
This paper cites The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey.
Evaluating Privilege Usage of Agents with Real-World Tools The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey
Reference 15
- Resolution
- malformed identifier
- arxiv_id, observed 2026-05-16T23:16:41.836860Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation fe4a2733-1029-46a8-850d-1e3042212830 · outbound
This paper cites VeriGuard: enhancing LLM agent safety via verified code generation.
Evaluating Privilege Usage of Agents with Real-World Tools VeriGuard: enhancing LLM agent safety via verified code generation
Reference 16
- Resolution
- verified exact
- arxiv_id, observed 2026-05-14T22:18:04.381176Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation daa8aea8-2c0e-4aca-b73b-8581d8f1edb3 · outbound
This paper cites an unresolved cited work.
Evaluating Privilege Usage of Agents with Real-World Tools Unresolved cited work
Reference 17
- Resolution
- unresolved
- raw_fallback, observed 2026-05-14T22:18:05.876423Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 75a85e32-fc8d-40be-8ff4-df27dc5fc9d9 · outbound
This paper cites OpenAI GPT-5 System Card.
Evaluating Privilege Usage of Agents with Real-World Tools OpenAI GPT-5 System Card
Reference 18
- Resolution
- verified exact
- local_arxiv, observed 2026-05-14T22:18:04.346670Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation f0986db5-7fd4-40a7-a930-7e1b012cec8e · outbound
This paper cites Qwen3 Technical Report.
Evaluating Privilege Usage of Agents with Real-World Tools Qwen3 Technical Report
Reference 19
- Resolution
- verified exact
- local_arxiv, observed 2026-05-14T22:18:04.387283Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 9539f15f-2afe-4e19-bdfd-63b130f52393 · outbound
This paper cites an unresolved cited work.
Evaluating Privilege Usage of Agents with Real-World Tools Unresolved cited work
Reference 20
- Resolution
- unresolved
- raw_fallback, observed 2026-05-14T22:18:05.880612Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 21457e76-a1e6-420d-8123-7a85410546f2 · outbound
This paper cites an unresolved cited work.
Evaluating Privilege Usage of Agents with Real-World Tools Unresolved cited work
Reference 21
- Resolution
- unresolved
- raw_fallback, observed 2026-05-14T22:18:05.885155Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 9d84ec95-b666-4ee4-b015-5eeac6927593 · outbound
This paper cites InCompanion Proceedings of the 32nd ACM International Conference on the Foundations of Software Engineering(Porto de Galinhas, Brazil)(FSE 2024).
Evaluating Privilege Usage of Agents with Real-World Tools InCompanion Proceedings of the 32nd ACM International Conference on the Foundations of Software Engineering(Porto de Galinhas, Brazil)(FSE 2024)
Reference 22
- Resolution
- verified exact
- arxiv_id, observed 2026-05-14T22:18:03.404372Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 6d2119fb-f001-4b5d-9e56-f64ea2a81a9e · outbound
This paper cites an unresolved cited work.
Evaluating Privilege Usage of Agents with Real-World Tools Unresolved cited work
Reference 23
- Resolution
- verified exact
- arxiv_id, observed 2026-05-14T22:18:03.386590Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Pith citing papers
Observation 806c1a05-acc3-4bad-b787-0c4378de9ccc · inbound
Kill-Chain Canaries: Stage-Level Tracking of Prompt Injection Across Attack Surfaces and Model Safety Tiers cites this paper.
Kill-Chain Canaries: Stage-Level Tracking of Prompt Injection Across Attack Surfaces and Model Safety Tiers Evaluating Privilege Usage of Agents with Real-World Tools
Reference 14
- Resolution
- verified exact
- local_arxiv, observed 2026-05-14T22:18:04.541116Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 00fb860b-50b0-46e9-824e-6493c1c3ed53 · inbound
Constraining Host-Level Abuse in Self-Hosted Computer-Use Agents via TEE-Backed Isolation cites this paper.
Constraining Host-Level Abuse in Self-Hosted Computer-Use Agents via TEE-Backed Isolation Evaluating Privilege Usage of Agents with Real-World Tools
Reference 43
- Resolution
- verified exact
- local_arxiv, observed 2026-05-11T20:26:10.968405Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 586ca2bf-c237-4689-aff5-94d4e3ccc569 · inbound
Do Coding Agents Understand Least-Privilege Authorization? cites this paper.
Do Coding Agents Understand Least-Privilege Authorization? Evaluating Privilege Usage of Agents with Real-World Tools
Reference 59
- Resolution
- verified exact
- local_arxiv, observed 2026-05-19T16:37:40.002337Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 8ac61058-bdd4-46c4-8c69-0cf78a278a75 · inbound
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback cites this paper.
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback Evaluating Privilege Usage of Agents with Real-World Tools
Reference 28
- Resolution
- verified exact
- local_arxiv, observed 2026-05-19T23:27:52.450166Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.