The Agent Skills Directory

[SAFE]: The skill establishes an MCP connection to api.cryptorefills.com, which is the official API infrastructure of the skill author, cryptorefills. This represents standard vendor-provided functionality for product discovery.
[INDIRECT_PROMPT_INJECTION]: The skill processes product descriptions and catalog data from a remote API, which is a standard attack surface for indirect prompt injection. However, the risk is effectively mitigated as the skill is strictly read-only and does not possess capabilities for file modification, command execution, or sensitive data access.

cryptorefills-catalog