invoice-revenue-audit
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data from the Stripe API, specifically invoice statuses, descriptions, and metadata. This creates a surface for indirect prompt injection where malicious instructions embedded in a Stripe record could attempt to influence the agent's reasoning.
- Ingestion points:
GetInvoices,stripe_api_search, andstripe_api_detailsfunctions (SKILL.md). - Boundary markers: Absent; the skill does not define specific delimiters to isolate external data from instructions.
- Capability inventory: Limited to Stripe API operations via the Stripe MCP; no capabilities for shell execution, file writing, or general network requests were found.
- Sanitization: The skill includes an instruction to "Never expose secret keys in output," which provides some data protection, though it lacks explicit input validation or escaping for the processed invoice content.
Audit Metadata