Paper Citation Record · LEDGER

Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills

As of 6 August 2026, this Paper Citation Record lists 28 of 28 outbound references and 0 inbound Pith citation observations for arXiv:2605.29354.

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

pith.paper-citation-record.v1
2605.29354 v1

Coverage vector

measured 28 of 28 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-29T06:58:47.841334Z

measured 28 of 28 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

28 of 28 outbound references displayed

verified exact0
verified fuzzy0
unresolved28
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 3970e82a-bfc5-48e7-8f40-3330055ef1f7 · outbound

This paper cites SoK: Attack and defense landscape of agentic AI systems.

Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills SoK: Attack and defense landscape of agentic AI systems

Reference 1

Resolution: unresolved; no resolver link, observed 2026-06-29T06:58:47.841334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5980a3a0-376e-4f5a-83fe-99a99792290d · outbound

This paper cites Research directions in software supply chain security.ACM Transactions on Software Engineering and Methodology, 34(5), 2025.

Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills Research directions in software supply chain security.ACM Transactions on Software Engineering and Methodology, 34(5), 2025

Reference 2

Resolution: unresolved; no resolver link, observed 2026-06-29T06:58:47.841334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6f70e84-9d2f-4d38-a689-b6ec2917c0b9 · outbound

This paper cites We have a package for you! a comprehensive analysis of package hallucinations by code generating LLMs.

Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills We have a package for you! a comprehensive analysis of package hallucinations by code generating LLMs

Reference 3

Resolution: unresolved; no resolver link, observed 2026-06-29T06:58:47.841334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc2de86d-ea46-4526-a380-53c46467c932 · outbound

This paper cites Importing phantoms: Measuring LLM package hallucination vulnerabilities, 2025.

Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills Importing phantoms: Measuring LLM package hallucination vulnerabilities, 2025

Reference 4

Resolution: unresolved; no resolver link, observed 2026-06-29T06:58:47.841334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c20f0379-29eb-4c6d-9e8d-00b95fe02fc9 · outbound

This paper cites HFUZZER: Testing large language models for package hallucinations via phrase-based fuzzing, 2025.

Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills HFUZZER: Testing large language models for package hallucinations via phrase-based fuzzing, 2025

Reference 5

Resolution: unresolved; no resolver link, observed 2026-06-29T06:58:47.841334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e5009bb-2fce-461a-8fa4-500277c28806 · outbound

This paper cites Trust me, import this: Dependency steering attacks via malicious agent skills, 2026.

Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills Trust me, import this: Dependency steering attacks via malicious agent skills, 2026

Reference 6

Resolution: unresolved; no resolver link, observed 2026-06-29T06:58:47.841334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0830f234-8d18-4501-a955-9f249ddc7702 · outbound

This paper cites LLM lies: Hallucinations are not bugs, but features as adversarial examples, 2023.

Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills LLM lies: Hallucinations are not bugs, but features as adversarial examples, 2023

Reference 7

Resolution: unresolved; no resolver link, observed 2026-06-29T06:58:47.841334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21e98668-78a8-4b49-abf7-870bc5c1fe79 · outbound

This paper cites HalluShift: Measuring distribution shifts towards hallucination detection in LLMs, 2025.

Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills HalluShift: Measuring distribution shifts towards hallucination detection in LLMs, 2025

Reference 8

Resolution: unresolved; no resolver link, observed 2026-06-29T06:58:47.841334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5ba9862-b529-47d7-b441-bbbe3cbbafff · outbound

This paper cites Trojan activation attack: Red-teaming large language models using activation steering for safety-alignment.

Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills Trojan activation attack: Red-teaming large language models using activation steering for safety-alignment

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-29T06:58:47.841334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 162ce65e-732d-44c7-b284-42bc6149c825 · outbound

This paper cites Steering language models before they speak: Logit-level interventions, 2026.

Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills Steering language models before they speak: Logit-level interventions, 2026

Reference 10

Resolution: unresolved; no resolver link, observed 2026-06-29T06:58:47.841334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 850a44d3-b867-40c7-995d-4cf12836798b · outbound

This paper cites RoleBreak: Character hallucination as a jailbreak attack in role-playing systems.

Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills RoleBreak: Character hallucination as a jailbreak attack in role-playing systems

Reference 11

Resolution: unresolved; no resolver link, observed 2026-06-29T06:58:47.841334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4849416-32ae-47e1-aa57-aec01c31fc23 · outbound

This paper cites Slopsquatting: Ai-generated code and supply chain risk, 2025.

Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills Slopsquatting: Ai-generated code and supply chain risk, 2025

Reference 12

Resolution: unresolved; no resolver link, observed 2026-06-29T06:58:47.841334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 859f9567-0077-4314-8cc7-f139e64cd976 · outbound

This paper cites Slopsquatting: When ai agents hallucinate malicious packages, 2025.

Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills Slopsquatting: When ai agents hallucinate malicious packages, 2025

Reference 13

Resolution: unresolved; no resolver link, observed 2026-06-29T06:58:47.841334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec441840-22eb-4536-b74d-b12b81018550 · outbound

This paper cites Qwen2.5- coder technical report, 2024.

Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills Qwen2.5- coder technical report, 2024

Reference 14

Resolution: unresolved; no resolver link, observed 2026-06-29T06:58:47.841334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6dffb0dc-a783-4bcf-a9e1-66178990bd2e · outbound

This paper cites an unresolved cited work.

Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills Unresolved cited work

Reference 15

Resolution: unresolved; no resolver link, observed 2026-06-29T06:58:47.841334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e2206a4-fb6b-459b-9342-5f4a03efbbcc · outbound

This paper cites an unresolved cited work.

Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills Unresolved cited work

Reference 16

Resolution: unresolved; no resolver link, observed 2026-06-29T06:58:47.841334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a161dfe2-a92a-4388-9ea2-42bac7d82482 · outbound

This paper cites an unresolved cited work.

Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills Unresolved cited work

Reference 17

Resolution: unresolved; no resolver link, observed 2026-06-29T06:58:47.841334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41d0b6df-0778-4974-b90e-0976b8a669ac · outbound

This paper cites an unresolved cited work.

Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills Unresolved cited work

Reference 18

Resolution: unresolved; no resolver link, observed 2026-06-29T06:58:47.841334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4c4c177-2fee-40db-b92d-9d3c937ca92b · outbound

This paper cites The illusionist’s prompt: Exposing the factual vulnerabilities of large language models with linguistic nuances, 2025.

Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills The illusionist’s prompt: Exposing the factual vulnerabilities of large language models with linguistic nuances, 2025

Reference 19

Resolution: unresolved; no resolver link, observed 2026-06-29T06:58:47.841334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 706288df-bab3-4013-877d-a84e6fceb62f · outbound

This paper cites A survey on large language model hallucination via a creativity perspective, 2024.

Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills A survey on large language model hallucination via a creativity perspective, 2024

Reference 20

Resolution: unresolved; no resolver link, observed 2026-06-29T06:58:47.841334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b339df9c-03bd-433d-93d6-1aa08260915d · outbound

This paper cites The illusion of progress: Re-evaluating hallucination detection in LLMs.

Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills The illusion of progress: Re-evaluating hallucination detection in LLMs

Reference 21

Resolution: unresolved; no resolver link, observed 2026-06-29T06:58:47.841334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc832a59-3525-4e99-a30e-5e948088bf86 · outbound

This paper cites hallucination.

Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills hallucination

Reference 22

Resolution: unresolved; no resolver link, observed 2026-06-29T06:58:47.841334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90bad096-5319-4a01-8be6-a6abb70079db · outbound

This paper cites an unresolved cited work.

Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills Unresolved cited work

Reference 23

Resolution: unresolved; no resolver link, observed 2026-06-29T06:58:47.841334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4541e899-6d3c-469c-b9ee-7cf557d1db17 · outbound

This paper cites an unresolved cited work.

Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills Unresolved cited work

Reference 24

Resolution: unresolved; no resolver link, observed 2026-06-29T06:58:47.841334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f330ad08-8634-45c1-b1f0-61d51fe9ea31 · outbound

This paper cites an unresolved cited work.

Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills Unresolved cited work

Reference 25

Resolution: unresolved; no resolver link, observed 2026-06-29T06:58:47.841334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31272aa7-0cc7-415f-a25d-f952b27810a2 · outbound

This paper cites 39 UNDERREVIEW- MAY29, 2026.

Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills 39 UNDERREVIEW- MAY29, 2026

Reference 26

Resolution: unresolved; no resolver link, observed 2026-06-29T06:58:47.841334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d13e84f-3a3e-42de-a7fa-a0486c03c890 · outbound

This paper cites an unresolved cited work.

Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills Unresolved cited work

Reference 27

Resolution: unresolved; no resolver link, observed 2026-06-29T06:58:47.841334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dec50998-857f-42f3-a334-6601c5eb5f2d · outbound

This paper cites Operation failed: {e}.

Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills Operation failed: {e}

Reference 28

Resolution: unresolved; no resolver link, observed 2026-06-29T06:58:47.841334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.