The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill downloads and installs the @membranehq/cli package from the official NPM registry to interact with the Membrane platform.
[COMMAND_EXECUTION]: The skill utilizes shell commands to manage Inedo Otter resources, including membrane action run and membrane action create for infrastructure automation.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from external Inedo Otter API responses.
Ingestion points: Runtime data retrieved via membrane action list and membrane action run output in SKILL.md.
Boundary markers: Absent; the instructions do not define clear delimiters for external data.
Capability inventory: The skill can execute automation logic and create new actions using the membrane CLI.
Sanitization: Not specified in the skill body; relies on the underlying platform's handling of action schemas.

inedo-otter