The Agent Skills Directory

[CREDENTIALS_UNSAFE]: The skill instructions proactively address credential safety by reminding the agent to advise users to keep secret API keys server-side and use publishable keys for client-side code. This aligns with standard security best practices for payment integrations.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data from official Stripe documentation at docs.stripe.com. While ingesting external content introduces a theoretical surface for indirect prompt injection, the target is a well-known and trusted service, and the skill does not grant the agent any dangerous capabilities such as file system writing or arbitrary command execution.
[SAFE]: All external references in the skill and the topic map point to the official docs.stripe.com domain. The skill is purely informational and serves to ground the agent's responses in authoritative, live documentation.

stripe-docs