The Agent Skills Directory

[SAFE]: The skill utilizes an external MCP server at https://rube.app/mcp and documentation from composio.dev. These are established services in the AI agent ecosystem for tool integration and do not pose an inherent security risk in this context.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection attack surface as it ingests untrusted data from Stripe records.
Ingestion points: Data retrieved through tools such as STRIPE_LIST_CUSTOMERS, STRIPE_SEARCH_INVOICES, and STRIPE_LIST_PRODUCTS (SKILL.md).
Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present in the tool sequences.
Capability inventory: The skill allows high-impact financial operations, including STRIPE_CREATE_REFUND, STRIPE_CREATE_PAYMENT_INTENT, and STRIPE_POST_CHARGES across various script logic.
Sanitization: No explicit sanitization or validation of the content of Stripe fields is specified within the skill instructions.

stripe-automation