The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external data from Stripe objects such as customer metadata, product descriptions, and invoice details which could be used to host malicious instructions.
Ingestion points: Data is ingested through search and list tools including STRIPE_SEARCH_CUSTOMERS, STRIPE_SEARCH_INVOICES, and STRIPE_LIST_PRODUCTS (SKILL.md).
Boundary markers: The instructions do not define specific delimiters or boundary markers to isolate data retrieved from Stripe from the agent's internal reasoning.
Capability inventory: The skill possesses significant financial capabilities including creating charges (STRIPE_CREATE_PAYMENT_INTENT), issuing refunds (STRIPE_CREATE_REFUND), and modifying subscriptions (STRIPE_UPDATE_SUBSCRIPTION).
Sanitization: While the skill includes a 'Limitations' section advising on verification and safety boundaries, it does not specify content sanitization for data pulled from Stripe fields.
[EXTERNAL_DOWNLOADS]: The skill instructs the agent/user to connect to an external Model Context Protocol (MCP) server.
Evidence: The Setup section in SKILL.md explicitly directs the configuration of https://rube.app/mcp as a remote server endpoint.

stripe-automation