quickbooks-online-api
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill describes patterns for ingesting and processing data from external API responses and webhooks, which constitutes a potential injection surface.
- Ingestion points: API response handlers and webhook processing logic defined in SKILL.md.
- Boundary markers: The provided code examples do not incorporate specific delimiters to isolate external data.
- Capability inventory: The skill demonstrates the use of network requests and state management (token persistence).
- Sanitization: Best practices for business logic validation are provided, but specific sanitization for LLM interpolation is not present.
Audit Metadata