billing-automation

Pass

Audited by Gen Agent Trust Hub on Oct 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill provides code patterns in references/details.md that interpolate untrusted data into HTML templates without sanitization, creating a vulnerability surface.
  • Ingestion points: Customer-supplied data such as customer_name and customer_address are used in the Invoice class.
  • Boundary markers: None present to distinguish between instructions and data within the template.
  • Capability inventory: The to_html method generates raw HTML strings that could be rendered by downstream systems or the agent.
  • Sanitization: The implementation uses Python's .format() method for string interpolation without escaping or validating the HTML content, which is a common vector for injection attacks.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 11, 2026, 05:19 AM