Artificial intelligence is increasingly integrated into professional cybersecurity workflows, yet the cognitive effects of AI assistance on researcher behavior remain poorly understood. This paper introduces the PTRR Framework, a structured metacognitive instrument designed to measure and mitigate Automation Bias in AI-assisted vulnerability research. PTRR comprises four components: Prompts (interaction quality scoring), Time (temporal behavioral analysis), Results (outcome-based severity scoring), and Rubric (process independence and verification criteria). Three derived indices operationalize the core constructs: the Automation Bias Index (ABI), which quantifies uncritical reliance on AI output; the Cognitive Struggle Index (CSI), which measures productive independent effort; and the Tool Integration Intensity Score (TIIS), which captures deliberate multi-tool synthesis. The framework is grounded in Dual Process Theory and Cognitive Load Theory, which together predict that expertise moderates the relationship between AI interaction quality and research output. A preliminary single-participant case study conducted over 60 structured hours provides initial construct validity evidence. The case study documented a shift from a low-to-medium severity finding profile to a critical-dominant profile following PTRR-based workflow adoption, including seven critical-severity findings validated by independent program triage and three multi-layer escalation chains. Total accepted findings increased from 2 to 11 over equivalent time periods. These results motivate the formal multi-participant study design proposed here as future work, which employs a within-subject Phase A versus Phase B design, Hierarchical Linear Modeling, and independent human scoring with pre-defined inter-rater reliability thresholds.