customer-billing-ops
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from customer communications and identifiers, creating a potential surface for indirect prompt injection attacks.
- Ingestion points: Support complaints, emails, and GitHub usernames processed during customer identification and issue classification as described in the Workflow section of SKILL.md.
- Boundary markers: The instructions lack specific delimiters or instructions for the agent to disregard commands embedded within the external customer data.
- Capability inventory: The skill authorizes the agent to perform state-changing operations including 'refund', 'cancel', and managing billing portals.
- Sanitization: There is no requirement for the agent to sanitize or validate the external text inputs before processing them.
Audit Metadata