The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs users to install the @membranehq/cli package globally from the NPM registry. This is a vendor-specific tool used to interact with the Membrane platform.
[COMMAND_EXECUTION]: The skill relies on executing membrane CLI commands to perform authentication, connection management, and API actions. These commands are executed locally in the user's environment to interface with the Seven API.
[PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection because it ingests and processes data from the Seven API (e.g., goals, habit details) which could contain adversarial instructions provided by third parties.
Ingestion points: Data returned from membrane action run and membrane request commands (SKILL.md).
Boundary markers: No specific boundary markers or instructions to ignore embedded commands are present in the skill's prompts or documentation.
Capability inventory: The skill possesses the capability to run further actions (membrane action run) and make network requests (membrane request), which could be leveraged if an injection is successful.
Sanitization: No sanitization, validation, or filtering logic for the incoming API data is mentioned in the skill definition.

seven