abridge-core-workflow-b
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a robust security posture focused on clinical data integrity and compliance. It explicitly forbids the use of production credentials, access to live patient charts without authorization, and exposure of session materials.
- [SAFE]: Instructions include clear boundaries for tool usage, restricting WebFetch to official documentation sources and requiring confirmation of environment and approval state before using Write or Edit tools.
- [SAFE]: The skill uses references/official-docs.md to point to legitimate, public support and press pages from Abridge, which are appropriate for the intended integration auditing task.
- [SAFE]: No obfuscation, prompt injection, or remote code execution patterns were detected in the instructions or reference materials.
Audit Metadata