The Agent Skills Directory

[SAFE]: The skill uses the Membrane platform to handle authentication, which is a security best practice as it prevents the exposure of API keys and secrets in the local environment.
[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the official Membrane CLI (@membranehq/cli) from the public NPM registry. This is a standard procedure for using the vendor's tooling and does not introduce unexpected third-party dependencies.
[COMMAND_EXECUTION]: The instructions involve running the membrane command-line tool. These commands are scoped to the intended functionality of managing connections and executing actions within the Vision6 integration.
[PROMPT_INJECTION]: The skill processes data from external sources (Vision6 reports, contacts), creating an indirect prompt injection surface.
Ingestion points: Results from membrane action run and membrane action list containing external data from Vision6.
Boundary markers: Absent; the skill does not specify delimiters for external data processing.
Capability inventory: Shell command execution via the membrane CLI.
Sanitization: Absent; the skill does not describe data sanitization procedures before agent consumption.

vision6