The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package from npm. This is the official command-line interface for the author's platform and is used to manage integrations safely.
[REMOTE_CODE_EXECUTION]: The skill utilizes npx to run the vendor's official CLI tool directly. This is a common developer workflow for ensuring the latest version of a utility is used.
[PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it processes data retrieved from the external Verve Group API.
Ingestion points: External data enters the agent's context through output from the membrane action run and membrane request commands.
Boundary markers: No specific delimiters or warnings to ignore embedded instructions are present in the provided documentation.
Capability inventory: The skill allows the agent to perform actions and make web requests through the membrane CLI tool.
Sanitization: There is no evidence of sanitization or filtering of the external data before it is presented to the agent.

verve