The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the membrane CLI to manage connections, search for actions, and execute integration logic with BuildBuddy.
[EXTERNAL_DOWNLOADS]: Fetches and installs the @membranehq/cli package from the NPM registry, which is the official tool provided by the vendor for interacting with their platform.
[PROMPT_INJECTION]: The skill exhibits an indirect injection surface by processing user-supplied intents and JSON inputs to interact with external services.
Ingestion points: SKILL.md (arguments for membrane action list and membrane action run commands)
Boundary markers: Absent
Capability inventory: Subprocess execution of the membrane CLI across several operational scripts
Sanitization: Not explicitly defined in the skill; sanitization is handled by the Membrane CLI and its server-side infrastructure.
[SAFE]: The skill follows security best practices by instructing the agent to never ask for or store API keys locally, delegating credential management to a secure external platform.

buildbuddy