real-world-evidence-study-designer
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates entirely as a text-based strategy assistant for clinical epidemiology. It provides instructions and reference modules to guide an AI agent in designing observational study protocols without invoking external tools or scripts.
- [SAFE]: No data exfiltration or credential exposure risks were identified. The skill references sensitive data types (EHR, claims, registries) only as subjects of study design and does not attempt to access or transmit actual database records.
- [SAFE]: No prompt injection or obfuscation patterns were detected. The instructions are transparent and focused on maintaining clinical research integrity, specifically warning against the fabrication of literature, PMIDs, or data capture capabilities.
- [SAFE]: The included evaluation report (eval_report_real-world-evidence-study-designer_result.json) was analyzed for malicious content; it is a static metadata artifact summarizing performance and safety checks and does not contain any executable code or malicious instructions.
Audit Metadata