The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package from the official npm registry. This is a standard requirement for using the vendor's platform tools.
[COMMAND_EXECUTION]: The skill executes various shell commands via the membrane CLI, including login, search, connect, and action run. These commands are used to manage the lifecycle of the Strapi integration and interact with the CMS data.
[PROMPT_INJECTION]: As an integration that retrieves data from an external CMS, the skill possesses an inherent surface for indirect prompt injection if the Strapi content contains malicious instructions.
Ingestion points: Data retrieved from Strapi via membrane action run and membrane request commands (found in SKILL.md).
Boundary markers: None are explicitly defined in the provided usage examples.
Capability inventory: Shell command execution via the membrane CLI (found in SKILL.md).
Sanitization: No specific sanitization or escaping logic is detailed; the skill relies on the agent's internal safety mechanisms when processing retrieved content.

strapi