The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the Membrane CLI from the official registry.
Evidence: npm install -g @membranehq/cli and npx @membranehq/cli@latest.
[COMMAND_EXECUTION]: Shell commands are used to interact with the Membrane platform for connection management and API execution.
Evidence: Commands such as membrane action run, membrane request, and membrane connect are executed via the CLI.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes data from Paubox which may contain untrusted content.
Ingestion points: Reads email content, organization data, and user records from the Paubox API (SKILL.md).
Boundary markers: Absent. No specific delimiters or instructions to ignore embedded commands are provided.
Capability inventory: Can execute API actions and send arbitrary HTTP requests via the Membrane proxy (SKILL.md).
Sanitization: Absent. The skill does not describe any validation or sanitization of data retrieved from Paubox.

paubox