The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the @membranehq/cli global npm package. This is the official tool provided by the vendor for interacting with their integration platform.
[COMMAND_EXECUTION]: The skill utilizes the membrane CLI for managing the integration lifecycle. This includes performing authentication via membrane login, establishing connections with membrane connect, and executing API operations via membrane action run.
[CREDENTIALS_UNSAFE]: The skill implements a secure authentication model. It correctly instructs users to use the Membrane platform's built-in OAuth and connection management instead of requesting or hardcoding sensitive API keys or tokens.
[PROMPT_INJECTION]: The skill processes data from external Formsite forms via the membrane action run command, which constitutes a surface for indirect prompt injection.
Ingestion points: Data from Formsite is returned to the agent context via the output of membrane action run in SKILL.md.
Boundary markers: The provided instructions do not specify any boundary markers or delimiters for the processed external content.
Capability inventory: The skill utilizes the membrane CLI to run and dynamically create actions based on natural language descriptions, as described in SKILL.md.
Sanitization: No specific sanitization or filtering of the ingested form data is mentioned in the skill instructions.

formsite