The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the @membranehq/cli package from the official NPM registry. This package is an official tool provided by the vendor 'membranedev' for managing API integrations.
[COMMAND_EXECUTION]: The skill uses the membrane CLI to authenticate, manage connections, and execute actions against the Sonix API. These commands are consistent with the platform's intended administrative and operational workflows.
[PROMPT_INJECTION]: The YAML frontmatter description incorrectly lists CRM-related objects (Deals, Persons, Leads) instead of transcription-related features, which appears to be a metadata consistency error.
[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it processes external transcription content while possessing command execution capabilities.
Ingestion points: External data is ingested into the agent context through the outputs of membrane action run and membrane request commands as described in SKILL.md.
Boundary markers: No delimiters or specific instructions to disregard embedded data patterns were found in the skill instructions.
Capability inventory: The skill allows for the execution of shell commands and network operations through the Membrane CLI (SKILL.md).
Sanitization: There are no mentioned mechanisms for sanitizing, escaping, or validating the data retrieved from the Sonix API before it is processed by the agent.

sonix