The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external data from Stripe (such as customer details, metadata, and webhook event payloads) which could be used as a vector for indirect prompt injection.
Ingestion points: Data is retrieved from the Stripe API via the stripe_customers, stripe_charges, and stripe_subscriptions tools.
Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the processed customer data.
Capability inventory: The skill has the capability to write to external systems (modifying subscriptions, issuing refunds) and exfiltrate data via reporting destinations like Slack and email.
Sanitization: There is no evidence of data sanitization or validation routines for external content before it is processed by the agent.

Stripe Payments