The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package from the npm registry. This is the official command-line tool for the Membrane platform and is considered a trusted vendor resource.
[COMMAND_EXECUTION]: Utilizes various membrane CLI commands to manage authentication, search for actions, and interact with the WatsonX AI API. These commands are used for their intended purpose within the Membrane ecosystem.
[DATA_EXFILTRATION]: Provides a proxy mechanism through the membrane request command to interact with external APIs. This method is used to securely inject authentication headers and manage tokens server-side, reducing the risk of exposing sensitive credentials locally.
[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes data from WatsonX AI API responses and action outputs (Ingestion: SKILL.md). This data can influence the parameters of subsequent actions (Capability: membrane action run). The skill relies on the platform's structured input schemas for safety. No explicit boundary markers or sanitization steps are defined in the markdown instructions.

watsonx-ai