The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill contains several curl commands designed to fetch content from https://fullstackrecipes.com. This retrieves external data from a domain not included in the trusted vendors or well-known services lists.
[INDIRECT_PROMPT_INJECTION]: The skill uses external content as instructions for the agent, creating a surface for indirect prompt injection.
Ingestion points: Multiple endpoints at fullstackrecipes.com/api/recipes/ are accessed to retrieve markdown content (e.g., config-schema-setup, neon-drizzle-setup, stripe-sync).
Boundary markers: There are no markers or instructions provided to the agent to treat the fetched content as untrusted or to ignore embedded instructions.
Capability inventory: The skill is designed to manage sensitive operations including database setup (Neon/Drizzle), environment variable configuration, and Stripe billing integration.
Sanitization: No sanitization, validation, or integrity checks (like checksums) are performed on the content fetched from the remote API before the agent processes it.

stripe-subscriptions