The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the membrane command-line interface to perform operations such as listing connections, searching for actions, and executing API requests. This is the intended functionality for managing Florm data.
[EXTERNAL_DOWNLOADS]: It requires the installation of the @membranehq/cli package via npm. This tool is provided by the vendor to facilitate secure interaction with their integration platform.
[DATA_EXFILTRATION]: The skill demonstrates safe data handling by leveraging Membrane's managed authentication system, which avoids the need for hardcoded credentials or manual API key entry.
[PROMPT_INJECTION]: The skill processes data from the Florm API, creating a surface for indirect prompt injection. This is a common characteristic of integration skills and does not involve malicious intent.
Ingestion points: Data returned from membrane action run and membrane request commands.
Boundary markers: None present.
Capability inventory: membrane action run, membrane request, membrane connect commands.
Sanitization: Not explicitly implemented in the skill instructions.

florm