The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to construct and execute shell commands using curl and jq. These commands include variables such as exchange, coin, fiat, and volumen. While the skill defines whitelists and validation steps, this pattern involves executing commands built from potentially untrusted user input.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from an external API, which creates a surface for indirect prompt injection if the remote source were to return malicious content designed to influence the agent's behavior.
Ingestion points: Responses from the criptoya.com API endpoints retrieved via curl as described in SKILL.md.
Boundary markers: The skill does not define specific delimiters or "ignore instructions" markers for the API output.
Capability inventory: The skill uses curl for network access and jq for JSON manipulation.
Sanitization: The workflow includes steps for input validation against defined whitelists for coins and exchanges, and specifies checking for text-based error responses ("Invalid pair") from the API.

crypto-prices-criptoya