invoice-document-pdf

Pass

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface due to the ingestion of untrusted external data that influences both output and automated actions.
  • Ingestion points: Data enters the agent's context through file-reading operations in BatchInvoiceProcessor.from_csv, BatchInvoiceProcessor.from_json, and InvoiceDeliverySystem.send_batch.
  • Boundary markers: There are no delimiters or specific instructions provided to the agent to treat processed data as untrusted or to ignore embedded instructions.
  • Capability inventory: The skill possesses capabilities for writing files to the local filesystem (PDF generation) and performing network operations via smtplib for email delivery.
  • Sanitization: The code lacks evidence of input validation, escaping, or filtering of content ingested from external data files before it is interpolated into document templates or email bodies.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 14, 2026, 01:02 PM
Security Audit — agent-trust-hub — invoice-document-pdf