The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli package via npm. This is a legitimate tool provided by the author to interface with the Membrane platform.
[COMMAND_EXECUTION]: The instructions leverage shell commands through the membrane CLI to handle authentication, connection lifecycle, and action execution. These commands are necessary for the skill's operational logic.
[PROMPT_INJECTION]: An indirect prompt injection surface (Category 8) was identified.
Ingestion points: The skill retrieves various financial records (invoices, contacts, reports) from the Xero API (SKILL.md).
Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the provided skill instructions.
Capability inventory: The skill possesses the capability to execute API actions (membrane action run) and perform raw network requests (membrane request) (SKILL.md).
Sanitization: No sanitization or validation of the retrieved Xero data is performed before it is processed by the agent.
[SAFE]: The skill follows security best practices by delegating authentication to the Membrane platform instead of requesting or storing sensitive API keys or OAuth tokens directly within the agent's context.

xero