price-check
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests data from external financial platforms which may contain untrusted content.
- Ingestion points: Revenue data, product/service names, and COGS from QuickBooks; gross sales data from PayPal.
- Boundary markers: None specified. The skill does not define delimiters or specific instructions to ignore embedded commands within the retrieved data.
- Capability inventory: The skill is configured with access to the
Bash,WebFetch, andReadtools. - Sanitization: The instructions do not include steps for validating, escaping, or filtering data retrieved from external APIs before it is incorporated into the agent's context.
Audit Metadata