clinical-differential-diagnosis
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides installation instructions via
npxand references its source code on GitHub (github.com/Open-Medica/open-medical-skills). These references target a recognized vendor (Open-Medica) and are documented as safe per vendor trust rules. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process patient clinical histories and laboratory results. While this creates a theoretical surface for indirect prompt injection if malicious instructions were embedded in the medical data, the risk is inherent to the skill's primary function and no exploitable capabilities for data exfiltration or system damage were identified.
Audit Metadata