accounts-payable-management
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill implements and tests the automated ingestion of invoices from external email attachments (PDF/images), which introduces a potential vector for malicious instructions embedded in the processed data.
- Ingestion points:
ingestInvoiceFromEmailprocesses external email attachments (identified inevals/three-way-matching-and-invoice-ingestion/task.md). - Boundary markers: Absent. The instructions do not specify the use of delimiters or 'ignore' directives for data extracted from attachments.
- Capability inventory: The skill manages financial records, initiates payment runs, and sends vendor notifications.
- Sanitization: Absent. There are no explicit requirements for sanitizing or escaping the text extracted via OCR before it is used in the matching or approval logic.
Audit Metadata