Paper Citation Record · LEDGER

Logic layer Prompt Control Injection (LPCI): A Novel Security Vulnerability Class in Agentic Systems

As of 11 August 2026, this Paper Citation Record lists 10 of 10 outbound references and 1 inbound Pith citation observation for arXiv:2507.10457.

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

pith.paper-citation-record.v1
2507.10457 v2

Coverage vector

measured 10 of 10 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T17:34:41.012242Z

measured 11 of 11 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-11T06:34:44.6726+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T15:40:52.686816Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-06T15:40:53.293923Z

Reference resolution

10 of 10 outbound references displayed

verified exact0
verified fuzzy5
unresolved5
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 3d6d3892-330b-4ef4-ba6b-49c54ecdc755 · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

Logic layer Prompt Control Injection (LPCI): A Novel Security Vulnerability Class in Agentic Systems Constitutional AI: Harmlessness from AI Feedback

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T17:34:40.979596Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f0a98ab-59e0-4dce-bf53-a7b3dcc501e3 · outbound

This paper cites CyberSecEval 2: A Wide-Ranging Cybersecurity Evaluation Suite for Large Language Models.

Logic layer Prompt Control Injection (LPCI): A Novel Security Vulnerability Class in Agentic Systems CyberSecEval 2: A Wide-Ranging Cybersecurity Evaluation Suite for Large Language Models

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T17:34:40.983819Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1288abbb-1d3d-4d66-bc4c-d36aed4532fd · outbound

This paper cites Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned.

Logic layer Prompt Control Injection (LPCI): A Novel Security Vulnerability Class in Agentic Systems Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T17:34:40.987575Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a77dce2d-abb8-4874-843d-9a4fa3a9498f · outbound

This paper cites CyberSecEval 2: A Wide-Ranging Cybersecurity Evaluation Suite for Large Language Models.

Logic layer Prompt Control Injection (LPCI): A Novel Security Vulnerability Class in Agentic Systems CyberSecEval 2: A Wide-Ranging Cybersecurity Evaluation Suite for Large Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T17:34:40.992014Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76e04d12-25b7-4d4a-90b2-9f8a2253f257 · outbound

This paper cites JSON Web Token (JWT),.

Logic layer Prompt Control Injection (LPCI): A Novel Security Vulnerability Class in Agentic Systems JSON Web Token (JWT),

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:34:41.119953Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 5d9de426-a51e-4820-8bc6-e83828edf601 · outbound

This paper cites ATLAS: Adversarial Threat Landscape for Artificial-Intelligence Systems,.

Logic layer Prompt Control Injection (LPCI): A Novel Security Vulnerability Class in Agentic Systems ATLAS: Adversarial Threat Landscape for Artificial-Intelligence Systems,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:34:41.110796Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 55f780b4-e192-4f91-9ed3-9afc3549a340 · outbound

This paper cites Trust No AI: Prompt Injection Along The CIA Security Triad.

Logic layer Prompt Control Injection (LPCI): A Novel Security Vulnerability Class in Agentic Systems Trust No AI: Prompt Injection Along The CIA Security Triad

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T17:34:41.002845Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d189fb9f-0644-45bd-ba79-5625a96749dd · outbound

This paper cites Spyware Injection Into Your ChatGPT’s Long-Term Memory (SpAI- ware),.

Logic layer Prompt Control Injection (LPCI): A Novel Security Vulnerability Class in Agentic Systems Spyware Injection Into Your ChatGPT’s Long-Term Memory (SpAI- ware),

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:34:41.101000Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation cf0840e9-1bc4-4578-aa9a-2a6a4d0fdeb0 · outbound

This paper cites OWASP Top 10 for Large Language Model Applications,.

Logic layer Prompt Control Injection (LPCI): A Novel Security Vulnerability Class in Agentic Systems OWASP Top 10 for Large Language Model Applications,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:34:41.091970Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 9babd59f-c144-4b40-9ed0-aad3936abbd4 · outbound

This paper cites 7 Container Security Best Practices for Enterprise Deployments,.

Logic layer Prompt Control Injection (LPCI): A Novel Security Vulnerability Class in Agentic Systems 7 Container Security Best Practices for Enterprise Deployments,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:34:41.081903Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Pith citing papers

Observation ca09cb54-2308-4910-a535-74d9dc080b1f · inbound

QSAF: A Novel Mitigation Framework for Cognitive Degradation in Agentic AI cites this paper.

QSAF: A Novel Mitigation Framework for Cognitive Degradation in Agentic AI Logic layer Prompt Control Injection (LPCI): A Novel Security Vulnerability Class in Agentic Systems

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-08-06T15:40:53.389894Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.