The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the user to execute membrane CLI commands to perform operations such as searching for connectors, establishing connections, and running specific Cody actions.
[EXTERNAL_DOWNLOADS]: The setup process involves installing the @membranehq/cli package from the npm registry, which is a common practice for platform-specific integrations and originates from the same author as the skill.
[PROMPT_INJECTION]: The skill possesses the capability to ingest untrusted data from external sources, specifically when creating documents from webpage URLs or listing messages. This represents a potential surface for indirect prompt injection, although the skill's design encourages the use of managed actions which typically incorporate safer handling than raw API calls.

cody