The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the @membranehq/cli package from the official NPM registry, which is the vendor's official command-line tool for platform integration.
[COMMAND_EXECUTION]: Utilizes shell-based commands (membrane) to perform authentication, manage connections, and execute blockchain actions within the intended scope of the skill.
[DATA_EXFILTRATION]: Specifically instructs the agent to use server-side authentication managed by the platform rather than requesting API keys from the user, preventing sensitive credential exposure in the local environment.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes natural language 'intents' and 'descriptions' to discover or generate actions.
Ingestion points: User-provided strings in membrane action list --intent and membrane action create commands within SKILL.md.
Boundary markers: None identified in the provided command templates.
Capability inventory: Execution of varied blockchain actions via the CLI as described in SKILL.md.
Sanitization: No explicit sanitization or validation of input strings is mentioned for the discovery process.

getblock