Paper Citation Record · LEDGER

How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study

As of 23 July 2026, this Paper Citation Record lists 25 of 25 outbound references and 11 inbound Pith citation observations for arXiv:2604.03070.

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

pith.paper-citation-record.v1
2604.03070 v2

Coverage vector

measured 25 of 25 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-13T13:34:41.548490Z

measured 36 of 36 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-07-23T06:31:01.910684+00:00

measured 11 of 11 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-12T09:11:24.259633Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-03T13:48:20.371575Z

Reference resolution

25 of 25 outbound references displayed

verified exact0
verified fuzzy0
unresolved25
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d4fa58c2-c861-413b-9691-940a885ae767 · outbound

This paper cites Aristotle: IMO-level Automated Theorem Proving.

How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study Aristotle: IMO-level Automated Theorem Proving

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-13T13:34:41.548490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f8c7103-1761-45f9-849a-297575f0e24b · outbound

This paper cites The equational theories project: Advancing collaborative mathematical research at scale.arXiv preprint arXiv:2512.07087,.

How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study The equational theories project: Advancing collaborative mathematical research at scale.arXiv preprint arXiv:2512.07087,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-13T13:34:41.548490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b031ba2d-ae0c-4c25-8246-2a4bdc1a0eef · outbound

This paper cites The future of mathematics? Talk slides, Pittsburgh, January 2020.https://www.andrew.cmu.edu/ user/avigad/meetings/fomm2020/slides/fomm_buzzard.pdf.

How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study The future of mathematics? Talk slides, Pittsburgh, January 2020.https://www.andrew.cmu.edu/ user/avigad/meetings/fomm2020/slides/fomm_buzzard.pdf

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-13T13:34:41.548490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e5f3023-7a1c-469a-aef6-60283b0b3554 · outbound

This paper cites Fel’s conjecture on syzygies of numerical semigroups, 2026.https://arxiv.org/abs/2602.03716.

How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study Fel’s conjecture on syzygies of numerical semigroups, 2026.https://arxiv.org/abs/2602.03716

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-13T13:34:41.548490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69b5eb20-be2a-477c-84d9-8237e39f242a · outbound

This paper cites Abstraction boundaries and spec driven development in pure mathematics.

How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study Abstraction boundaries and spec driven development in pure mathematics

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-13T13:34:41.548490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90452797-8029-40ac-94fb-f3323324ef0d · outbound

This paper cites STP: Self-play LLM Theorem Provers with Iterative Conjecturing and Proving.

How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study STP: Self-play LLM Theorem Provers with Iterative Conjecturing and Proving

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-13T13:34:41.548490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17853244-36b3-4f8c-981f-36a1b6941a1a · outbound

This paper cites An Introduction to Algebraic Combinatorics.

How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study An Introduction to Algebraic Combinatorics

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-13T13:34:41.548490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bfeec12a-2ce3-4837-b129-ed2961905809 · outbound

This paper cites The price of progress: Algorithmic efficiency and the falling cost of ai inference, 2025.https://arxiv.org/abs/2511.23455.

How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study The price of progress: Algorithmic efficiency and the falling cost of ai inference, 2025.https://arxiv.org/abs/2511.23455

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-13T13:34:41.548490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e972be0-64e1-43e8-86aa-b30a25dd9c03 · outbound

This paper cites Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs.

How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-13T13:34:41.548490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27d15ec0-f38e-47de-80d9-c98dbe6e17ab · outbound

This paper cites Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs.

How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-13T13:34:41.548490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c50715db-26dc-4f20-960b-f461ea0a60f6 · outbound

This paper cites Hongjian Li.

How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study Hongjian Li

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-13T13:34:41.548490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bed2fef2-5733-40f4-8679-166b090d6782 · outbound

This paper cites Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction.

How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-13T13:34:41.548490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1777f116-638c-456a-8d32-5811f2c52f6f · outbound

This paper cites Numina-lean-agent: An open and general agentic reasoning system for formal mathematics.

How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study Numina-lean-agent: An open and general agentic reasoning system for formal mathematics

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-13T13:34:41.548490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7a05003-5676-4dd5-8f01-87d324d1e6f9 · outbound

This paper cites At Which Training Stage Does Code Data Help LLMs Reasoning?.

How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study At Which Training Stage Does Code Data Help LLMs Reasoning?

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-13T13:34:41.548490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 712f5c84-338d-4967-8fd6-6849b1fd9ada · outbound

This paper cites Math, Inc.

How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study Math, Inc

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-13T13:34:41.548490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bcf49d97-abbe-4334-b15f-7e81c6e935f1 · outbound

This paper cites 3373824.http://dx.doi.org/10.1145/3372885.3373824.

How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study 3373824.http://dx.doi.org/10.1145/3372885.3373824

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-13T13:34:41.548490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14c79605-64cd-4c6c-b1bb-b4d00b86dab2 · outbound

This paper cites DeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal Decomposition.

How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study DeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal Decomposition

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-13T13:34:41.548490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e325edba-37b5-4c80-9780-ead44335b109 · outbound

This paper cites Watershed moment for ai–human collaboration in math.IEEE Spectrum, March 2026.https: //spectrum.ieee.org/ai-proof-verification.

How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study Watershed moment for ai–human collaboration in math.IEEE Spectrum, March 2026.https: //spectrum.ieee.org/ai-proof-verification

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-13T13:34:41.548490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 120cf064-676b-45aa-87e5-7b25108f8e60 · outbound

This paper cites Floris van Doorn, Patrick Massot, and Oliver Nash.

How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study Floris van Doorn, Patrick Massot, and Oliver Nash

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-13T13:34:41.548490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad91aad4-caa8-4538-a085-05b4ef6d2e72 · outbound

This paper cites ISBN 9798400700262.

How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study ISBN 9798400700262

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-13T13:34:41.548490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6904891d-a13f-461f-964b-239dc7a1b0fb · outbound

This paper cites Opinion piece.

How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study Opinion piece

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-13T13:34:41.548490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2765feb-9124-440e-a788-650787328a15 · outbound

This paper cites Kimina-Prover Preview: Towards Large Formal Reasoning Models with Reinforcement Learning.

How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study Kimina-Prover Preview: Towards Large Formal Reasoning Models with Reinforcement Learning

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-13T13:34:41.548490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a286a8d-a65d-482a-8764-e050a284fc7b · outbound

This paper cites DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search.

How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-13T13:34:41.548490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59b16279-bbb5-4599-8360-e3769e0ffe68 · outbound

This paper cites Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs.

How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-13T13:34:41.548490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a487f89e-88e2-4416-9b5b-838984be8b26 · outbound

This paper cites Unveiling the Impact of Coding Data Instruction Fine-Tuning on Large Language Models Reasoning.

How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study Unveiling the Impact of Coding Data Instruction Fine-Tuning on Large Language Models Reasoning

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-13T13:34:41.548490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation f51c76e0-a7f8-46ab-a027-fdeef1f8ef88 · inbound

RouteGuard: Internal-Signal Detection of Skill Poisoning in LLM Agents cites this paper.

RouteGuard: Internal-Signal Detection of Skill Poisoning in LLM Agents How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-11T19:36:14.825969Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation ff327533-35c1-4ddb-b16d-1a552e55b2d3 · inbound

Trust Me, Import This: Dependency Steering Attacks via Malicious Agent Skills cites this paper.

Trust Me, Import This: Dependency Steering Attacks via Malicious Agent Skills How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-05-12T06:56:27.283904Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 1b3953c3-2bb8-44a1-b84b-c5b6b9a47e6e · inbound

AgentTrap: Measuring Runtime Trust Failures in Third-Party Agent Skills cites this paper.

AgentTrap: Measuring Runtime Trust Failures in Third-Party Agent Skills How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study

Reference 2

Resolution: metadata mismatch; local_arxiv, observed 2026-05-15T05:45:06.714012Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 4814a289-4017-4afb-9212-9d3748b7c1fe · inbound

When Safe Skills Collide: Measuring Compositional Risk in Agent Skill Ecosystems cites this paper.

When Safe Skills Collide: Measuring Compositional Risk in Agent Skill Ecosystems How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-06-28T19:52:36.018699Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 8e17e250-c1f4-4321-91f4-12a7f66924d7 · inbound

SeClaw: Spec-Driven Security Task Synthesis for Evaluating Autonomous Agents cites this paper.

SeClaw: Spec-Driven Security Task Synthesis for Evaluating Autonomous Agents How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-07-01T23:56:23.018601Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 6bba19e0-1049-4cb9-a0fa-2e726fd7bc96 · inbound

Harnessing Agent Skills: Architectural Patterns and a Reference Architecture for Skill-Mediated LLM Agents cites this paper.

Harnessing Agent Skills: Architectural Patterns and a Reference Architecture for Skill-Mediated LLM Agents How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study

Reference 76

Resolution: metadata mismatch; local_arxiv, observed 2026-06-28T22:42:46.513546Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 3bbf8f63-a143-471c-af14-786189b3dbd7 · inbound

From Registry to Repository: How AI Agent Skills Are Written, Adapted, and Maintained cites this paper.

From Registry to Repository: How AI Agent Skills Are Written, Adapted, and Maintained How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-07-02T08:36:47.568568Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation ea19cd92-d2d8-450e-98c4-a8c3a015a142 · inbound

From Registry to Repository: How AI Agent Skills Are Written, Adapted, and Maintained cites this paper.

From Registry to Repository: How AI Agent Skills Are Written, Adapted, and Maintained How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-12T09:11:24.259633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4debb845-b80d-4e27-80b5-7e4caf6297ec · inbound

Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification cites this paper.

Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-07-03T13:48:20.372743Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 2f7e8a33-df69-4b89-9929-ded4241d2d0a · inbound

Cloak and Detonate: Scanner Evasion and Dynamic Detection of Agent Skill Malware cites this paper.

Cloak and Detonate: Scanner Evasion and Dynamic Detection of Agent Skill Malware How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-07-03T10:37:56.221104Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation f6a7ee81-6fbf-4c69-909f-f913c4d9e824 · inbound

Cloak and Detonate: Scanner Evasion and Dynamic Detection of Agent Skill Malware cites this paper.

Cloak and Detonate: Scanner Evasion and Dynamic Detection of Agent Skill Malware How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-12T08:09:57.596812Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.