fluentcart-orders-transactions
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill allows the agent to process external data that could contain malicious instructions.
- Ingestion points: Untrusted data enters the agent context through payment provider objects and webhook reconciliation as described in SKILL.md.
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for external data strings.
- Capability inventory: The skill performs sensitive operations including mutating database tables (fct_orders, fct_order_transactions), processing financial refunds, and dispatching lifecycle hooks as detailed in SKILL.md and references/order-event-map.md.
- Sanitization: Although the skill suggests verifying signatures and amounts, there is no guidance on sanitizing or escaping ingested strings before they are interpolated into the agent's prompt context.
Audit Metadata