The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill recommends installing the @membranehq/cli package via npm. This is a documented dependency provided by the skill vendor (Membrane) to facilitate service integration.
[COMMAND_EXECUTION]: The skill utilizes the membrane command-line tool to manage connections and execute actions. These operations are restricted to the functionality provided by the Membrane platform and do not involve arbitrary shell execution.
[PROMPT_INJECTION]: The skill processes external data from Placetel via membrane action run. This creates an indirect prompt injection surface as the agent may ingest untrusted content from the phone system.
Ingestion points: Output from membrane action run in SKILL.md.
Boundary markers: Not present; the instructions do not specify delimiters for external data.
Capability inventory: Command execution through the membrane CLI and connection management.
Sanitization: Not present; the skill relies on the agent's default handling of tool outputs.
[CREDENTIALS_UNSAFE]: The skill explicitly instructs the agent to avoid asking for user credentials (API keys or tokens), directing users toward Membrane's server-side connection management, which is a positive security practice.

placetel