billing-automation

Pass

Audited by Gen Agent Trust Hub on Mar 31, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill implements an indirect prompt injection surface within the Invoice.to_html method, which generates HTML documents using unsanitized data.
  • Ingestion points: External customer data such as customer.name and customer.address provided to the Invoice class in SKILL.md.
  • Boundary markers: No delimiters or instructions are used to isolate untrusted data within the HTML template.
  • Capability inventory: The skill provides logic for generating structured HTML documents from templates via string interpolation in SKILL.md.
  • Sanitization: The code lacks any escaping, filtering, or validation of user-controlled strings before they are embedded into the markup.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 31, 2026, 02:03 AM
Security Audit — agent-trust-hub — billing-automation