The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package globally via npm. This is the official command-line interface provided by the skill author for interacting with their platform.
[COMMAND_EXECUTION]: The instructions involve executing shell commands using the membrane CLI, including login, connect, and action run. These commands are standard for managing authentication and executing platform tasks.
[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it handles user-provided input in commands:
Ingestion points: User-supplied strings are passed to the --intent flag in membrane action list and the --input flag in membrane action run within SKILL.md.
Boundary markers: Examples in the documentation do not explicitly demonstrate the use of delimiters or 'ignore' instructions for the interpolated user content.
Capability inventory: The skill can execute actions on the Marvel API and create new functional actions via the membrane CLI as described in SKILL.md.
Sanitization: Documentation does not specify client-side sanitization; validation is expected to be managed by the Membrane platform.

marvel