customer-billing-ops

Pass

Audited by Gen Agent Trust Hub on Sep 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data to drive sensitive billing decisions.
  • Ingestion points: Reads customer emails, support tickets, and GitHub usernames to identify users and classify billing issues (SKILL.md).
  • Boundary markers: The instructions do not define clear delimiters or "ignore embedded instructions" markers for the processed customer data.
  • Capability inventory: The skill has the capability to modify subscription states, issue refunds, and generate customer-facing communications based on its analysis of external input.
  • Sanitization: There are no instructions for sanitizing or escaping the content retrieved from external customer communications before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 12, 2026, 03:39 PM
Security Audit — agent-trust-hub — customer-billing-ops