abridge-upgrade-migration

Pass

Audited by Gen Agent Trust Hub on Apr 25, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Potential surface for indirect prompt injection discovered in the migration workflow.
  • Ingestion points: Clinical templates and documentation are ingested via the migrateTemplates function in src/migration/template-migration.ts.
  • Boundary markers: No boundary markers or instructions to ignore embedded content are present in the processing logic.
  • Capability inventory: The skill has access to Read, Write, Edit, and Bash tools, which could be misused if injected instructions are followed.
  • Sanitization: While the code removes structural EHR metadata, it lacks validation or sanitization of the natural language content within the ingested templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 25, 2026, 06:51 PM
Security Audit — agent-trust-hub — abridge-upgrade-migration