Paper Citation Record · LEDGER

Intent-Governed Tool Authorization for AI Agents

As of 8 August 2026, this Paper Citation Record lists 29 of 29 outbound references and 2 inbound Pith citation observations for arXiv:2606.22916.

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

pith.paper-citation-record.v1
2606.22916 v3

Coverage vector

measured 29 of 29 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T10:32:34.305658Z

measured 31 of 31 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T21:46:23.178867Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-07T21:46:23.228007Z

Reference resolution

29 of 29 outbound references displayed

verified exact0
verified fuzzy0
unresolved29
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 35e4b550-9009-4b6e-a0c5-77af0bd29a83 · outbound

This paper cites Mitchell, and Helen Nissenbaum.

Intent-Governed Tool Authorization for AI Agents Mitchell, and Helen Nissenbaum

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T10:32:34.190015Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ad0b115-7c52-4a14-bf3e-af0d0a81cb75 · outbound

This paper cites StruQ: Defending Against Prompt Injection with Structured Queries, 2024.

Intent-Governed Tool Authorization for AI Agents StruQ: Defending Against Prompt Injection with Structured Queries, 2024

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T10:32:34.195425Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6925ba9-b5db-4f60-947d-7fd4af1dd12e · outbound

This paper cites AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents, 2024.

Intent-Governed Tool Authorization for AI Agents AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents, 2024

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T10:32:34.200454Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d6554e7-29dd-475e-b524-7a9b20ba8dd0 · outbound

This paper cites Ferraiolo and D.

Intent-Governed Tool Authorization for AI Agents Ferraiolo and D

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T10:32:34.204718Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0f6652c-2c24-4d45-a1d0-def0189e696e · outbound

This paper cites Operationalizing Contextual Integrity in Privacy-Conscious Assistants, 2024.

Intent-Governed Tool Authorization for AI Agents Operationalizing Contextual Integrity in Privacy-Conscious Assistants, 2024

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-02T10:32:34.209047Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5148af58-0ae0-44f1-8027-39fb613b014a · outbound

This paper cites AttriGuard: Defeating Indirect Prompt Injection in LLM Agents via Causal Attribution of Tool Invocations, 2026.

Intent-Governed Tool Authorization for AI Agents AttriGuard: Defeating Indirect Prompt Injection in LLM Agents via Causal Attribution of Tool Invocations, 2026

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-02T10:32:34.213183Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95a6121f-b61e-4f21-abb2-81c8b95b9eee · outbound

This paper cites Hu, David Ferraiolo, D.

Intent-Governed Tool Authorization for AI Agents Hu, David Ferraiolo, D

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T10:32:34.217976Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aadee338-8424-4dab-bc4b-2a7b4a7e7a9d · outbound

This paper cites Model Context Protocol Threat Modeling and Analyzing Vulnerabilities to Prompt Injection with Tool Poisoning, 2026.

Intent-Governed Tool Authorization for AI Agents Model Context Protocol Threat Modeling and Analyzing Vulnerabilities to Prompt Injection with Tool Poisoning, 2026

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T10:32:34.221964Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 155969ce-f6d2-48af-b01b-39ac1b6ec51a · outbound

This paper cites Need to Know: Contextual-Integrity-Grounded Query Rewriting for Privacy-Conscious LLM Delegation, 2026.

Intent-Governed Tool Authorization for AI Agents Need to Know: Contextual-Integrity-Grounded Query Rewriting for Privacy-Conscious LLM Delegation, 2026

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T10:32:34.226055Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc683ac0-ffc0-49de-bb82-d0b72c09f240 · outbound

This paper cites Securing the Model Context Protocol: Defending LLMs Against Tool Poisoning and Adversarial Attacks, 2025.

Intent-Governed Tool Authorization for AI Agents Securing the Model Context Protocol: Defending LLMs Against Tool Poisoning and Adversarial Attacks, 2025

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T10:32:34.230584Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04527dff-7c3f-442d-a8ec-6f0de9fb2625 · outbound

This paper cites AgentDyn: A Dynamic Open-Ended Benchmark for Evaluating Prompt Injection Attacks of Real-World Agent Security System, 2026.

Intent-Governed Tool Authorization for AI Agents AgentDyn: A Dynamic Open-Ended Benchmark for Evaluating Prompt Injection Attacks of Real-World Agent Security System, 2026

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T10:32:34.234585Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07390d51-9322-4ebd-b180-551a78573fc9 · outbound

This paper cites ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities, 2024.

Intent-Governed Tool Authorization for AI Agents ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities, 2024

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T10:32:34.238425Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1ba5f8d-8550-411d-af00-4b72ce3fe447 · outbound

This paper cites Authorization.

Intent-Governed Tool Authorization for AI Agents Authorization

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T10:32:34.242656Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce07bee1-4c59-4d39-846f-8db0deceea91 · outbound

This paper cites an unresolved cited work.

Intent-Governed Tool Authorization for AI Agents Unresolved cited work

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T10:32:34.246480Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4305c0a2-561c-46c6-a159-87cd8ffc45bb · outbound

This paper cites Artificial Intelligence Risk Management Framework: Generative Artificial Intelligence Profile.

Intent-Governed Tool Authorization for AI Agents Artificial Intelligence Risk Management Framework: Generative Artificial Intelligence Profile

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T10:32:34.250987Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 317a95c7-4542-42b8-965f-5bcff794f96d · outbound

This paper cites Stanford University Press, 2009.

Intent-Governed Tool Authorization for AI Agents Stanford University Press, 2009

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T10:32:34.254698Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 248fada8-082e-454e-bf66-5b1528e87fe2 · outbound

This paper cites LLM01:2025 Prompt Injection.

Intent-Governed Tool Authorization for AI Agents LLM01:2025 Prompt Injection

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T10:32:34.258538Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea0dbd09-bbb0-40bd-b484-24a0b327d865 · outbound

This paper cites OW ASP Top 10 for LLM Applications 2025.

Intent-Governed Tool Authorization for AI Agents OW ASP Top 10 for LLM Applications 2025

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-02T10:32:34.262506Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12854581-b907-4f19-8917-076c26188621 · outbound

This paper cites Maddison, and Tatsunori Hashimoto.

Intent-Governed Tool Authorization for AI Agents Maddison, and Tatsunori Hashimoto

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-02T10:32:34.266439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24193b09-c495-4e28-a941-85aa18df27b7 · outbound

This paper cites Saltzer and Michael D.

Intent-Governed Tool Authorization for AI Agents Saltzer and Michael D

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T10:32:34.270482Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18747825-aa31-4fc9-846d-f4d8f8e1e8e5 · outbound

This paper cites MCP-38: A Comprehensive Threat Taxonomy for Model Context Protocol Systems, 2026.

Intent-Governed Tool Authorization for AI Agents MCP-38: A Comprehensive Threat Taxonomy for Model Context Protocol Systems, 2026

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-02T10:32:34.274818Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eebae825-626a-4ea0-84ab-2ac6ce20bfb7 · outbound

This paper cites Prompt Injection Attack to Tool Selection in LLM Agents, 2025.

Intent-Governed Tool Authorization for AI Agents Prompt Injection Attack to Tool Selection in LLM Agents, 2025

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-02T10:32:34.278453Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00621fd8-9e55-4b4d-bda7-b74ec9383132 · outbound

This paper cites ToolTweak: An Attack on Tool Selection in LLM-based Agents, 2025.

Intent-Governed Tool Authorization for AI Agents ToolTweak: An Attack on Tool Selection in LLM-based Agents, 2025

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-02T10:32:34.282521Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98643bf9-498f-43c6-9087-381d3c6661fd · outbound

This paper cites Data Guard: A Fine-grained Purpose-based Access Control System for Large Data Warehouses, 2025.

Intent-Governed Tool Authorization for AI Agents Data Guard: A Fine-grained Purpose-based Access Control System for Large Data Warehouses, 2025

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-02T10:32:34.286490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e214b054-0206-4d5e-b16d-f35e9c1af57b · outbound

This paper cites MCPTox: A Benchmark for Tool Poisoning Attack on Real-World MCP Servers, 2025.

Intent-Governed Tool Authorization for AI Agents MCPTox: A Benchmark for Tool Poisoning Attack on Real-World MCP Servers, 2025

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-02T10:32:34.290321Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16334e18-31fb-4d43-803b-2114a0d375c8 · outbound

This paper cites Messaging with Purpose Limitation – Privacy-Compliant Publish-Subscribe Systems, 2021.

Intent-Governed Tool Authorization for AI Agents Messaging with Purpose Limitation – Privacy-Compliant Publish-Subscribe Systems, 2021

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-02T10:32:34.294081Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf519791-baee-479a-aa36-7bbec0918fb1 · outbound

This paper cites τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains, 2024.

Intent-Governed Tool Authorization for AI Agents τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains, 2024

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-02T10:32:34.297969Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 425f23c7-a4f1-4650-9752-c017d720c82f · outbound

This paper cites InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents, 2024.

Intent-Governed Tool Authorization for AI Agents InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents, 2024

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-02T10:32:34.301794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8d8d1d6-3e6d-47e0-b085-4800c10f72d7 · outbound

This paper cites AgentSentry: Mitigating Indirect Prompt Injection in LLM Agents via Temporal Causal Diagnostics and Context Purification, 2026.

Intent-Governed Tool Authorization for AI Agents AgentSentry: Mitigating Indirect Prompt Injection in LLM Agents via Temporal Causal Diagnostics and Context Purification, 2026

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-02T10:32:34.305658Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 889e1901-795c-4aed-8869-f65b2837f1dd · inbound

Explanation-Bound Tool Execution for AI Agents: Server-Verified Action Claims Without Trusting Model Rationales cites this paper.

Explanation-Bound Tool Execution for AI Agents: Server-Verified Action Claims Without Trusting Model Rationales Intent-Governed Tool Authorization for AI Agents

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-01T02:43:24.437055Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fdc261ba-1e82-46d5-a9b2-c2aa5dc85c59 · inbound

The Vulnerability With No CVE: Managing Persistent Gaps Between Mandate and Authority in AI Coding Agents cites this paper.

The Vulnerability With No CVE: Managing Persistent Gaps Between Mandate and Authority in AI Coding Agents Intent-Governed Tool Authorization for AI Agents

Reference 40

Resolution: metadata mismatch; local_arxiv, observed 2026-08-07T21:46:23.233895Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.