Summary

A Prompt injection vulnerability has been discovered affecting multiple models. The specific flaw manifests when an attacker frames the synthesis of a Schedule II compound derived from piperidone and aniline as an academic reconstruction exercise, incrementally requesting clarification on individual steps such as acylation conditions, reductive amination reagents, pH-controlled workup procedures, storage stability, and waste disposal, thereby presenting each request as legitimate laboratory technique discussion rather than an explicit drug manufacturing query. This stepwise, chemistry-focused framing causes the models to provide detailed reagents, solvents, purification methods, and handling considerations that collectively reconstruct the full synthesis and post-processing workflow, and allows the attacker to obtain actionable guidance for manufacturing controlled opioid compounds.