Skills
skills/aaaaqwq/agi-super-skills/billing-automation/Gen Agent Trust Hub

billing-automation

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill references the stripe Python library for payment handling and the reportlab library for PDF generation. Both are well-known and trusted resources for their respective functions.\n- [PROMPT_INJECTION]: Vulnerabilities to indirect prompt injection exist in the Invoice.to_html and DunningManager.send_email methods within resources/implementation-playbook.md. These methods interpolate customer-controlled data, such as names and addresses, directly into HTML and email templates using string formatting without sanitization or escaping.\n
  • Ingestion points: Invoice and DunningManager classes in resources/implementation-playbook.md (processing customer identity and location data).\n
  • Boundary markers: None implemented to delimit untrusted external data.\n
  • Capability inventory: Includes financial transaction processing via stripe.Charge.create and automated communication via send_email.\n
  • Sanitization: No escaping or validation is performed on inputs before interpolation into templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 07:55 AM