The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the @membranehq/cli package globally via npm (npm install -g @membranehq/cli@latest). This tool is provided by the vendor and is necessary for managing integrations and authentication.- [COMMAND_EXECUTION]: The skill relies on executing membrane CLI commands for authentication (membrane login), connection management (membrane connect), and data operations (membrane action run).- [PROMPT_INJECTION]: As the skill ingests and processes data from the Harmonic SaaS platform and uses it within the agent's context, it presents an indirect prompt injection surface. 1. Ingestion points: Data returned from membrane action run commands. 2. Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are used when processing external data. 3. Capability inventory: The agent can execute shell commands via the Membrane CLI. 4. Sanitization: No explicit sanitization or validation of the external content is performed before interpolation into the prompt.

harmonic