The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the @membranehq/cli package from NPM. This is the official command-line tool provided by the vendor to facilitate the integration and manage connections.
[COMMAND_EXECUTION]: The skill uses the membrane CLI to search for actions, run commands, and proxy requests to the Zenkit API. These operations are the intended primary purpose of the skill and are performed through a managed interface.
[CREDENTIALS_UNSAFE]: The skill demonstrates high security standards by explicitly advising against asking users for API keys or tokens. It uses a server-side connection model that handles authentication and credential refresh automatically without local secret exposure.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from an external source (Zenkit), which presents a potential surface for indirect prompt injection if those records contain malicious instructions.
Ingestion points: Zenkit records, items, and comments retrieved via CLI commands in SKILL.md.
Boundary markers: Not present.
Capability inventory: Execution of shell commands via the membrane CLI.
Sanitization: Not specified in the skill instructions.

zenkit