account-opening-workflow

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill describes a workflow for processing untrusted external data which constitutes a surface for indirect prompt injection.
  • Ingestion points: Intake of account opening requests from clients and advisors via onboarding platforms, CRM, and email (SKILL.md).
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are included in the workflow.
  • Capability inventory: The described workflow involves updating critical internal records (CRM, PMS, billing) and initiating financial trades.
  • Sanitization: No specific measures for semantic validation or sanitization of incoming data are mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 07:27 AM