abridge-webhooks-events
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill focuses on secure implementation patterns for healthcare integrations. It includes explicit warnings against hardcoding credentials, reusing production secrets, and committing private payload data.
- [EXTERNAL_DOWNLOADS]: The skill references and fetches content from official Abridge domains (abridge.com, trust.abridge.com) and the U.S. Department of Health and Human Services (hhs.gov). These are well-known, authoritative sources for healthcare product and regulatory documentation.
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an ingestion surface by using
WebFetchto read external documentation. This risk is mitigated by strict instructional boundaries that limit fetches to official sources and require manual reconciliation if public guidance differs from tenant-specific documentation. Capabilities are restricted to synthetic data testing unless manual approval is obtained. - [DATA_EXFILTRATION]: While the skill uses
WebFetch, its use is limited to known documentation sites. The instructions specifically forbid the transmission of patient data (PHI) and session identifiers to unauthorized endpoints.
Audit Metadata