The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli package from the NPM registry to interact with the Membrane platform. This is a standard dependency for skills utilizing the Membrane ecosystem.
[COMMAND_EXECUTION]: The skill relies on executing shell commands via the membrane CLI. These commands are used for logging in, connecting to the Review Studio connector, and running specific actions like listing or creating tasks.
[PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it processes content from Review Studio documents and annotations. 1. Ingestion points: Data is retrieved from the Review Studio API through the membrane action run command. 2. Boundary markers: The skill does not explicitly define markers to separate retrieved data from agent instructions. 3. Capability inventory: The skill has the capability to execute further actions and CLI commands based on the context. 4. Sanitization: The skill relies on the underlying Membrane platform and the agent's own safety filters for data sanitization.

reviewstudio