The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the @membranehq/cli package from NPM. This is the official CLI tool provided by the skill's vendor (Membrane) and is required for the integration logic.
[COMMAND_EXECUTION]: The skill utilizes the membrane CLI to perform various operations, including authentication (membrane login), connecting to external services (membrane connect), and executing API actions (membrane action run). These commands are standard for the intended use case of the platform.
[PROMPT_INJECTION]: An indirect prompt injection surface is identified where user-supplied queries are passed to the membrane action list command via the --intent flag and JSON parameters are passed to membrane action run.
Ingestion points: User input is interpolated into the --intent and --input flags in SKILL.md.
Boundary markers: None explicitly defined in the CLI command examples.
Capability inventory: The skill can perform network operations and authenticate to services via the membrane CLI.
Sanitization: None described within the skill instructions, relying on the CLI and agent's internal handling.

currencyapi