The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package from the NPM registry. This is a standard utility provided by the vendor for interacting with their platform.
[COMMAND_EXECUTION]: The skill makes extensive use of the membrane command-line tool to manage connections, list actions, and execute requests. These commands are necessary for the skill's primary functionality and are used in a structured manner.
[PROMPT_INJECTION]: The skill interacts with external decision data, which introduces an indirect prompt injection surface. * Ingestion points: External data is ingested through actions like List Decisions, Get Decision, and through direct API requests via membrane request as described in SKILL.md. * Boundary markers: There are no explicit markers or instructions provided to the agent to differentiate between system instructions and data fetched from the Decision Journal. * Capability inventory: The skill has the ability to write or modify data using Update Decision, Create Decision, and membrane action run commands as documented in SKILL.md. * Sanitization: No specific sanitization or validation logic is defined for the content retrieved from the external service.

decision-journal