The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes data from external API responses that could contain malicious instructions, creating a potential attack surface.
Ingestion points: The skill retrieves data from the Stripe API through the stripe CLI, including customer information, product details, and invoice metadata (referenced in SKILL.md and manifest.yaml).
Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat data from the API as untrusted or to ignore any embedded instructions.
Capability inventory: The skill allows the agent to call tools that modify or delete data in the Stripe account, such as data.modify and data.delete (defined in manifest.yaml).
Sanitization: No sanitization or validation mechanisms are described for data fetched from the external API before it is utilized in the agent's context.
[COMMAND_EXECUTION]: The skill executes the stripe CLI binary to manage merchant accounts and perform payment-related tasks. This is the intended and standard method for this service integration.
[SAFE]: The skill connects to well-known Stripe domains (mcp.stripe.com, access.stripe.com) for API communication and authentication, which is appropriate for its stated purpose.

stripe