The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the uxc command-line tool to interface with Model Context Protocol (MCP) servers. It creates a local alias crypto-com-mcp-cli using the uxc link command to manage interactions with the remote endpoint.
[EXTERNAL_DOWNLOADS]: The skill connects to the official Crypto.com MCP endpoint at https://mcp.crypto.com/market-data/mcp. This targets a well-known cryptocurrency exchange service and is used as intended for market data discovery.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from a remote API which represents a potential attack surface for indirect prompt injection.
Ingestion points: Data is fetched from https://mcp.crypto.com/market-data/mcp via the uxc tool as described in SKILL.md.
Boundary markers: The skill instructs the agent to focus on the JSON output envelope and stable fields, but does not implement explicit delimiters or markers to separate untrusted data from instructions.
Capability inventory: The skill performs shell command execution using uxc and its created aliases.
Sanitization: There is no evidence of programmatic sanitization or filtering of the API responses before they are processed by the agent.

crypto-com-mcp-skill