med-vault

Pass

Audited by Gen Agent Trust Hub on Jul 1, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [SAFE]: The skill's design focuses on local data management, explicitly stating that medication records remain on the user's device and avoid unauthorized cloud transmission.
  • [EXTERNAL_DOWNLOADS]: External data queries are restricted to trusted, well-known government medical databases such as OpenFDA and the National Library of Medicine's RxNorm and DailyMed services.
  • [SAFE]: Potential indirect prompt injection from processing external data (OCR of medication labels) is mitigated by mandatory human-in-the-loop confirmation steps where the user must verify extracted data before it is saved.
  • [DATA_EXFILTRATION]: No malicious data exfiltration patterns or unauthorized network operations were detected in the skill's instructions, metadata, or supporting documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 1, 2026, 12:28 PM
Security Audit — agent-trust-hub — med-vault