The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package from the npm registry. This is the official command-line interface for the Membrane platform associated with the skill author.
[COMMAND_EXECUTION]: The skill makes extensive use of the membrane CLI to manage authentication, search for Twilio actions, and execute them. These operations are within the scope of the skill's intended purpose.
[DATA_EXPOSURE]: The skill avoids the use of hardcoded credentials and explicitly advises against asking users for tokens or API keys, delegating secret management to the Membrane platform. This reduces the risk of credential leakage in logs or prompts.
[PROMPT_INJECTION]: Analysis for indirect prompt injection (Category 8):
Ingestion points: Data returned from membrane action run (e.g., Twilio message bodies, recording metadata) entering the agent context via terminal output.
Boundary markers: None identified in the provided instructions.
Capability inventory: Execution of shell commands via the membrane CLI.
Sanitization: No specific sanitization or escaping logic is described for handling external Twilio data before it is processed by the agent.

twilio