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

A machine-verified record of the checks Pith has run against this paper: detector runs, findings, signed bundle events, and canonical identifiers.

arXiv:2605.29354 · pith:2026:G7UPK5UY5ZV6LYBHIB4OSTDHFZ

0Critical

0Advisory

3Detectors run

2026-06-05Last checked

Paper page arXiv integrity.json bundle.json

Detector runs

ai_meta_artifact skipped v1.0.0 · findings 0 · 2026-06-05 05:35:51.108826+00:00

claim_evidence completed v1.0.0 · findings 0 · 2026-06-03 19:28:35.390667+00:00

cited_work_retraction completed v1.0.0 · findings 0 · 2026-05-29 17:54:49.245865+00:00

Findings

No public integrity findings for this paper.

Signed record

The machine-readable record for this paper lives at /pith/G7UPK5UY/integrity.json. Pith Number bundles also include signed pith.integrity.v1 events where a Pith Number exists.