The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the @membranehq/cli package globally via NPM. This is a verified vendor resource from 'membranedev' used to interact with their platform and the AppDrag service securely.
[COMMAND_EXECUTION]: The skill utilizes the membrane command-line interface to perform operations such as listing connections, discovering actions, and executing API requests. These commands are necessary for the skill's core functionality.
[PROMPT_INJECTION]: As a data-driven integration that interacts with external AppDrag content (e.g., blog posts, member lists, database records), there is a surface for indirect prompt injection.
- Ingestion points: Data returned from AppDrag actions through the membrane CLI.
- Boundary markers: Not explicitly defined in the instructions.
- Capability inventory: SQL query execution, file system operations, and email dispatching.
- Sanitization: The skill relies on the underlying agent's standard safety protocols for processing external data.

appdrag