The Agent Skills Directory

[SAFE]: The skill provides a legitimate set of instructions for managing JustCall data via the Membrane CLI. All external resources, including the npm package @membranehq/cli and the getmembrane.com domain, are official resources from the vendor (membranedev).
[COMMAND_EXECUTION]: The skill guides the user to perform operations using the membrane CLI. This is the intended primary functionality for this integration and does not involve unauthorized activities or dangerous shell patterns.
[PROMPT_INJECTION]: The skill processes external data from JustCall (such as SMS messages and contact notes) which could contain instructions intended to influence the agent's behavior (indirect prompt injection). This is an inherent surface for communication skills.
Ingestion points: Data is retrieved from the JustCall API using membrane action run and membrane request commands in SKILL.md.
Boundary markers: No specific delimiters or "ignore" instructions are provided for handling external data.
Capability inventory: The skill utilizes the membrane CLI for network requests and data management as described in SKILL.md.
Sanitization: No explicit sanitization or validation of the retrieved content is described in the skill instructions.

justcall