The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the @membranehq/cli package from the official npm registry. This is a vendor-owned resource used to manage the integration.
[COMMAND_EXECUTION]: The skill uses the membrane CLI to perform operations like authentication and action execution. These commands are part of the intended functionality for the platform integration.
[SAFE]: The skill follows security best practices by instructing the agent never to ask the user for API keys or tokens, instead delegating authentication to the Membrane platform's server-side connection manager.
[PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it ingests untrusted web data via ScrapeNinja.
Ingestion points: Web data retrieved via membrane action run as described in SKILL.md.
Boundary markers: None explicitly defined.
Capability inventory: membrane action create and membrane action run commands in SKILL.md.
Sanitization: None explicitly mentioned; relies on the agent's internal safety filters and platform managed environment.

scrapeninja