The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the official Membrane CLI (@membranehq/cli) globally via npm. This is a standard dependency for skills interacting with the Membrane ecosystem.
[COMMAND_EXECUTION]: Uses the membrane CLI to manage connections and execute GTmetrix-related actions. The instructions guide the user through a secure authentication flow that avoids local credential storage.
[PROMPT_INJECTION]: The skill ingests data from external GTmetrix reports, which is a common surface for indirect prompt injection in tool-oriented skills.
Ingestion points: Data retrieved from action outputs in SKILL.md (e.g., via membrane action run).
Boundary markers: None explicitly defined to separate tool output from agent instructions.
Capability inventory: The agent can execute CLI commands and manage connections through the provided instructions.
Sanitization: No specific sanitization logic is provided for external report data, which is typical for this type of integration.

gtmetrix