onboard-a-list
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external email list data which constitutes an untrusted input surface.
- Ingestion points: Data is ingested through the
ReadListSnapshot.capturePageport described inreferences/contracts.md, which retrieves contact, preference, activity, and automation facts from external source accounts. - Boundary markers: The instructions require that provider-specific terminology be contained within adapters and that all external data be decoded into owned domain schemas.
- Capability inventory: Across
SKILL.mdandreferences/contracts.md, the skill describes capabilities for reading from source account APIs, performing DNS lookups, and writing to destination email service providers. - Sanitization: The skill utilizes the
Effectlibrary'sSchemamodule to strictly validate and decode all external inputs (e.g.,decodeListImportPolicy) before they are processed by the planner or importer.
Audit Metadata